Chris Xiaoxuan Lu

Alexander Rutherford, Benjamin Ellis, Matteo Gallici et al. · deepmind, meta-ai

Benchmarks are crucial in the development of machine learning algorithms, with available environments significantly influencing reinforcement learning (RL) research. Traditionally, RL environments run on the CPU, which limits their scalability with typical academic compute. However, recent advancements in JAX have enabled the wider use of hardware acceleration, enabling massively parallel RL training pipelines and environments. While this has been successfully applied to single-agent RL, it has not yet been widely adopted for multi-agent scenarios. In this paper, we present JaxMARL, the first open-source, Python-based library that combines GPU-enabled efficiency with support for a large number of commonly used MARL environments and popular baseline algorithms. Our experiments show that, in terms of wall clock time, our JAX-based training pipeline is around 14 times faster than existing approaches, and up to 12500x when multiple training runs are vectorized. This enables efficient and thorough evaluations, potentially alleviating the evaluation crisis in the field. We also introduce and benchmark SMAX, a JAX-based approximate reimplementation of the popular StarCraft Multi-Agent Challenge, which removes the need to run the StarCraft II game engine. This not only enables GPU acceleration, but also provides a more flexible MARL environment, unlocking the potential for self-play, meta-learning, and other future applications in MARL. The code is available at https://github.com/flairox/jaxmarl.

Jianfei Yang, Xinyan Chen, Dazhuo Wang et al. · berkeley

WiFi sensing has been evolving rapidly in recent years. Empowered by propagation models and deep learning methods, many challenging applications are realized such as WiFi-based human activity recognition and gesture recognition. However, in contrast to deep learning for visual recognition and natural language processing, no sufficiently comprehensive public benchmark exists. In this paper, we review the recent progress on deep learning enabled WiFi sensing, and then propose a benchmark, SenseFi, to study the effectiveness of various deep learning models for WiFi sensing. These advanced models are compared in terms of distinct sensing tasks, WiFi platforms, recognition accuracy, model size, computational complexity, feature transferability, and adaptability of unsupervised learning. It is also regarded as a tutorial for deep learning based WiFi sensing, starting from CSI hardware platform to sensing algorithms. The extensive experiments provide us with experiences in deep model design, learning strategy skills and training techniques for real-world applications. To the best of our knowledge, this is the first benchmark with an open-source library for deep learning in WiFi sensing research. The benchmark codes are available at https://github.com/xyanchen/WiFi-CSI-Sensing-Benchmark.

Aaditya Singh, Adam Fry, Adam Perelman et al. · berkeley, mila

This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reasoning model for harder problems, and a real-time router that quickly decides which model to use based on conversation type, complexity, tool needs, and explicit intent (for example, if you say 'think hard about this' in the prompt). The router is continuously trained on real signals, including when users switch models, preference rates for responses, and measured correctness, improving over time. Once usage limits are reached, a mini version of each model handles remaining queries. This system card focuses primarily on gpt-5-thinking and gpt-5-main, while evaluations for other models are available in the appendix. The GPT-5 system not only outperforms previous models on benchmarks and answers questions more quickly, but -- more importantly -- is more useful for real-world queries. We've made significant advances in reducing hallucinations, improving instruction following, and minimizing sycophancy, and have leveled up GPT-5's performance in three of ChatGPT's most common uses: writing, coding, and health. All of the GPT-5 models additionally feature safe-completions, our latest approach to safety training to prevent disallowed content. Similarly to ChatGPT agent, we have decided to treat gpt-5-thinking as High capability in the Biological and Chemical domain under our Preparedness Framework, activating the associated safeguards. While we do not have definitive evidence that this model could meaningfully help a novice to create severe biological harm -- our defined threshold for High capability -- we have chosen to take a precautionary approach.

Fangqiang Ding, Andras Palffy, Dariu M. Gavrila et al.

This work proposes a novel approach to 4D radar-based scene flow estimation via cross-modal learning. Our approach is motivated by the co-located sensing redundancy in modern autonomous vehicles. Such redundancy implicitly provides various forms of supervision cues to the radar scene flow estimation. Specifically, we introduce a multi-task model architecture for the identified cross-modal learning problem and propose loss functions to opportunistically engage scene flow estimation using multiple cross-modal constraints for effective model training. Extensive experiments show the state-of-the-art performance of our method and demonstrate the effectiveness of cross-modal supervised learning to infer more accurate 4D radar scene flow. We also show its usefulness to two subtasks - motion segmentation and ego-motion estimation. Our source code will be available on https://github.com/Toytiny/CMFlow.

Lang Deng, Jianfei Yang, Shenghai Yuan et al. · berkeley

As an important biomarker for human identification, human gait can be collected at a distance by passive sensors without subject cooperation, which plays an essential role in crime prevention, security detection and other human identification applications. At present, most research works are based on cameras and computer vision techniques to perform gait recognition. However, vision-based methods are not reliable when confronting poor illuminations, leading to degrading performances. In this paper, we propose a novel multimodal gait recognition method, namely GaitFi, which leverages WiFi signals and videos for human identification. In GaitFi, Channel State Information (CSI) that reflects the multi-path propagation of WiFi is collected to capture human gaits, while videos are captured by cameras. To learn robust gait information, we propose a Lightweight Residual Convolution Network (LRCN) as the backbone network, and further propose the two-stream GaitFi by integrating WiFi and vision features for the gait retrieval task. The GaitFi is trained by the triplet loss and classification loss on different levels of features. Extensive experiments are conducted in the real world, which demonstrates that the GaitFi outperforms state-of-the-art gait recognition methods based on single WiFi or camera, achieving 94.2% for human identification tasks of 12 subjects.

Chris Lu, Yannick Schroecker, Albert Gu et al.

Structured state space sequence (S4) models have recently achieved state-of-the-art performance on long-range sequence modeling tasks. These models also have fast inference speeds and parallelisable training, making them potentially useful in many reinforcement learning settings. We propose a modification to a variant of S4 that enables us to initialise and reset the hidden state in parallel, allowing us to tackle reinforcement learning tasks. We show that our modified architecture runs asymptotically faster than Transformers in sequence length and performs better than RNN's on a simple memory-based task. We evaluate our modified architecture on a set of partially-observable environments and find that, in practice, our model outperforms RNN's while also running over five times faster. Then, by leveraging the model's ability to handle long-range sequences, we achieve strong performance on a challenging meta-learning task in which the agent is given a randomly-sampled continuous control environment, combined with a randomly-sampled linear projection of the environment's observations and actions. Furthermore, we show the resulting model can adapt to out-of-distribution held-out tasks. Overall, the results presented in this paper show that structured state space models are fast and performant for in-context reinforcement learning tasks. We provide code at https://github.com/luchris429/popjaxrl.

Chris Lu, Jakub Grudzien Kuba, Alistair Letcher et al. · deepmind

Tremendous progress has been made in reinforcement learning (RL) over the past decade. Most of these advancements came through the continual development of new algorithms, which were designed using a combination of mathematical derivations, intuitions, and experimentation. Such an approach of creating algorithms manually is limited by human understanding and ingenuity. In contrast, meta-learning provides a toolkit for automatic machine learning method optimisation, potentially addressing this flaw. However, black-box approaches which attempt to discover RL algorithms with minimal prior structure have thus far not outperformed existing hand-crafted algorithms. Mirror Learning, which includes RL algorithms, such as PPO, offers a potential middle-ground starting point: while every method in this framework comes with theoretical guarantees, components that differentiate them are subject to design. In this paper we explore the Mirror Learning space by meta-learning a "drift" function. We refer to the immediate result as Learnt Policy Optimisation (LPO). By analysing LPO we gain original insights into policy optimisation which we use to formulate a novel, closed-form RL algorithm, Discovered Policy Optimisation (DPO). Our experiments in Brax environments confirm state-of-the-art performance of LPO and DPO, as well as their transfer to unseen settings.

Zhijun Pan, Fangqiang Ding, Hantao Zhong et al.

Mobile autonomy relies on the precise perception of dynamic environments. Robustly tracking moving objects in 3D world thus plays a pivotal role for applications like trajectory prediction, obstacle avoidance, and path planning. While most current methods utilize LiDARs or cameras for Multiple Object Tracking (MOT), the capabilities of 4D imaging radars remain largely unexplored. Recognizing the challenges posed by radar noise and point sparsity in 4D radar data, we introduce RaTrack, an innovative solution tailored for radar-based tracking. Bypassing the typical reliance on specific object types and 3D bounding boxes, our method focuses on motion segmentation and clustering, enriched by a motion estimation module. Evaluated on the View-of-Delft dataset, RaTrack showcases superior tracking precision of moving objects, largely surpassing the performance of the state of the art. We release our code and model at https://github.com/LJacksonPan/RaTrack.

Matthew Thomas Jackson, Minqi Jiang, Jack Parker-Holder et al. · oxford

The past decade has seen vast progress in deep reinforcement learning (RL) on the back of algorithms manually designed by human researchers. Recently, it has been shown that it is possible to meta-learn update rules, with the hope of discovering algorithms that can perform well on a wide range of RL tasks. Despite impressive initial results from algorithms such as Learned Policy Gradient (LPG), there remains a generalization gap when these algorithms are applied to unseen environments. In this work, we examine how characteristics of the meta-training distribution impact the generalization performance of these algorithms. Motivated by this analysis and building on ideas from Unsupervised Environment Design (UED), we propose a novel approach for automatically generating curricula to maximize the regret of a meta-learned optimizer, in addition to a novel approximation of regret, which we name algorithmic regret (AR). The result is our method, General RL Optimizers Obtained Via Environment Design (GROOVE). In a series of experiments, we show that GROOVE achieves superior generalization to LPG, and evaluate AR against baseline metrics from UED, identifying it as a critical component of environment design in this setting. We believe this approach is a step towards the discovery of truly general RL algorithms, capable of solving a wide range of real-world environments.

Fangqiang Ding, Zhen Luo, Peijun Zhao et al.

Human motion sensing plays a crucial role in smart systems for decision-making, user interaction, and personalized services. Extensive research that has been conducted is predominantly based on cameras, whose intrusive nature limits their use in smart home applications. To address this, mmWave radars have gained popularity due to their privacy-friendly features. In this work, we propose milliFlow, a novel deep learning approach to estimate scene flow as complementary motion information for mmWave point cloud, serving as an intermediate level of features and directly benefiting downstream human motion sensing tasks. Experimental results demonstrate the superior performance of our method when compared with the competing approaches. Furthermore, by incorporating scene flow information, we achieve remarkable improvements in human activity recognition and human parsing and support human body part tracking. Code and dataset are available at https://github.com/Toytiny/milliFlow.

Changhao Chen, Bing Wang, Chris Xiaoxuan Lu et al.

Deep learning based localization and mapping approaches have recently emerged as a new research direction and receive significant attentions from both industry and academia. Instead of creating hand-designed algorithms based on physical models or geometric theories, deep learning solutions provide an alternative to solve the problem in a data-driven way. Benefiting from the ever-increasing volumes of data and computational power on devices, these learning methods are fast evolving into a new area that shows potentials to track self-motion and estimate environmental model accurately and robustly for mobile agents. In this work, we provide a comprehensive survey, and propose a taxonomy for the localization and mapping methods using deep learning. This survey aims to discuss two basic questions: whether deep learning is promising to localization and mapping; how deep learning should be applied to solve this problem. To this end, a series of localization and mapping topics are investigated, from the learning based visual odometry, global relocalization, to mapping, and simultaneous localization and mapping (SLAM). It is our hope that this survey organically weaves together the recent works in this vein from robotics, computer vision and machine learning communities, and serves as a guideline for future researchers to apply deep learning to tackle the problem of visual localization and mapping.

Dongjiang Cao, Ruofeng Liu, Hao Li et al.

Human identification is a key requirement for many applications in everyday life, such as personalized services, automatic surveillance, continuous authentication, and contact tracing during pandemics, etc. This work studies the problem of cross-modal human re-identification (ReID), in response to the regular human movements across camera-allowed regions (e.g., streets) and camera-restricted regions (e.g., offices) deployed with heterogeneous sensors. By leveraging the emerging low-cost RGB-D cameras and mmWave radars, we propose the first-of-its-kind vision-RF system for cross-modal multi-person ReID at the same time. Firstly, to address the fundamental inter-modality discrepancy, we propose a novel signature synthesis algorithm based on the observed specular reflection model of a human body. Secondly, an effective cross-modal deep metric learning model is introduced to deal with interference caused by unsynchronized data across radars and cameras. Through extensive experiments in both indoor and outdoor environments, we demonstrate that our proposed system is able to achieve ~92.5% top-1 accuracy and ~97.5% top-5 accuracy out of 56 volunteers. We also show that our proposed system is able to robustly reidentify subjects even when multiple subjects are present in the sensors' field of view.

Robert Tjarko Lange, Tom Schaul, Yutian Chen et al.

Optimizing functions without access to gradients is the remit of black-box methods such as evolution strategies. While highly general, their learning dynamics are often times heuristic and inflexible - exactly the limitations that meta-learning can address. Hence, we propose to discover effective update rules for evolution strategies via meta-learning. Concretely, our approach employs a search strategy parametrized by a self-attention-based architecture, which guarantees the update rule is invariant to the ordering of the candidate solutions. We show that meta-evolving this system on a small set of representative low-dimensional analytic optimization problems is sufficient to discover new evolution strategies capable of generalizing to unseen optimization problems, population sizes and optimization horizons. Furthermore, the same learned evolution strategy can outperform established neuroevolution baselines on supervised and continuous control tasks. As additional contributions, we ablate the individual neural network components of our method; reverse engineer the learned strategy into an explicit heuristic form, which remains highly competitive; and show that it is possible to self-referentially train an evolution strategy from scratch, with the learned update rule used to drive the outer meta-learning loop.

Alexander David Goldie, Chris Lu, Matthew Thomas Jackson et al.

While reinforcement learning (RL) holds great potential for decision making in the real world, it suffers from a number of unique difficulties which often need specific consideration. In particular: it is highly non-stationary; suffers from high degrees of plasticity loss; and requires exploration to prevent premature convergence to local optima and maximize return. In this paper, we consider whether learned optimization can help overcome these problems. Our method, Learned Optimization for Plasticity, Exploration and Non-stationarity (OPEN), meta-learns an update rule whose input features and output structure are informed by previously proposed solutions to these difficulties. We show that our parameterization is flexible enough to enable meta-learning in diverse learning contexts, including the ability to use stochasticity for exploration. Our experiments demonstrate that when meta-trained on single and small sets of environments, OPEN outperforms or equals traditionally used optimizers. Furthermore, OPEN shows strong generalization characteristics across a range of environments and agent architectures.

Stephen Zhao, Chris Lu, Roger Baker Grosse et al.

Learning With Opponent-Learning Awareness (LOLA) (Foerster et al. [2018a]) is a multi-agent reinforcement learning algorithm that typically learns reciprocity-based cooperation in partially competitive environments. However, LOLA often fails to learn such behaviour on more complex policy spaces parameterized by neural networks, partly because the update rule is sensitive to the policy parameterization. This problem is especially pronounced in the opponent modeling setting, where the opponent's policy is unknown and must be inferred from observations; in such settings, LOLA is ill-specified because behaviorally equivalent opponent policies can result in non-equivalent updates. To address this shortcoming, we reinterpret LOLA as approximating a proximal operator, and then derive a new algorithm, proximal LOLA (POLA), which uses the proximal formulation directly. Unlike LOLA, the POLA updates are parameterization invariant, in the sense that when the proximal objective has a unique optimum, behaviorally equivalent policies result in behaviorally equivalent updates. We then present practical approximations to the ideal POLA update, which we evaluate in several partially competitive environments with function approximation and opponent modeling. This empirically demonstrates that POLA achieves reciprocity-based cooperation more reliably than LOLA.

Robert Tjarko Lange, Tom Schaul, Yutian Chen et al.

Genetic algorithms constitute a family of black-box optimization algorithms, which take inspiration from the principles of biological evolution. While they provide a general-purpose tool for optimization, their particular instantiations can be heuristic and motivated by loose biological intuition. In this work we explore a fundamentally different approach: Given a sufficiently flexible parametrization of the genetic operators, we discover entirely new genetic algorithms in a data-driven fashion. More specifically, we parametrize selection and mutation rate adaptation as cross- and self-attention modules and use Meta-Black-Box-Optimization to evolve their parameters on a set of diverse optimization tasks. The resulting Learned Genetic Algorithm outperforms state-of-the-art adaptive baseline genetic algorithms and generalizes far beyond its meta-training settings. The learned algorithm can be applied to previously unseen optimization problems, search dimensions & evaluation budgets. We conduct extensive analysis of the discovered operators and provide ablation experiments, which highlight the benefits of flexible module parametrization and the ability to transfer (`plug-in') the learned operators to conventional genetic algorithms.

Andrew Jesson, Chris Lu, Gunshi Gupta et al.

This paper proposes a step toward approximate Bayesian inference in on-policy actor-critic deep reinforcement learning. It is implemented through three changes to the Asynchronous Advantage Actor-Critic (A3C) algorithm: (1) applying a ReLU function to advantage estimates, (2) spectral normalization of actor-critic weights, and (3) incorporating \emph{dropout as a Bayesian approximation}. We prove under standard assumptions that restricting policy updates to positive advantages optimizes for value by maximizing a lower bound on the value function plus an additive term. We show that the additive term is bounded proportional to the Lipschitz constant of the value function, which offers theoretical grounding for spectral normalization of critic weights. Finally, our application of dropout corresponds to approximate Bayesian inference over both the actor and critic parameters, which enables \textit{adaptive state-aware} exploration around the modes of the actor via Thompson sampling. We demonstrate significant improvements for median and interquartile mean metrics over A3C, PPO, SAC, and TD3 on the MuJoCo continuous control benchmark and improvement over PPO in the challenging ProcGen generalization benchmark.

Fangqiang Ding, Zhijun Pan, Yimin Deng et al.

Scene flow allows autonomous vehicles to reason about the arbitrary motion of multiple independent objects which is the key to long-term mobile autonomy. While estimating the scene flow from LiDAR has progressed recently, it remains largely unknown how to estimate the scene flow from a 4-D radar - an increasingly popular automotive sensor for its robustness against adverse weather and lighting conditions. Compared with the LiDAR point clouds, radar data are drastically sparser, noisier and in much lower resolution. Annotated datasets for radar scene flow are also in absence and costly to acquire in the real world. These factors jointly pose the radar scene flow estimation as a challenging problem. This work aims to address the above challenges and estimate scene flow from 4-D radar point clouds by leveraging self-supervised learning. A robust scene flow estimation architecture and three novel losses are bespoken designed to cope with intractable radar data. Real-world experimental results validate that our method is able to robustly estimate the radar scene flow in the wild and effectively supports the downstream task of motion segmentation.

Chris Lu, Timon Willi, Christian Schroeder de Witt et al.

In general-sum games, the interaction of self-interested learning agents commonly leads to collectively worst-case outcomes, such as defect-defect in the iterated prisoner's dilemma (IPD). To overcome this, some methods, such as Learning with Opponent-Learning Awareness (LOLA), shape their opponents' learning process. However, these methods are myopic since only a small number of steps can be anticipated, are asymmetric since they treat other agents as naive learners, and require the use of higher-order derivatives, which are calculated through white-box access to an opponent's differentiable learning algorithm. To address these issues, we propose Model-Free Opponent Shaping (M-FOS). M-FOS learns in a meta-game in which each meta-step is an episode of the underlying inner game. The meta-state consists of the inner policies, and the meta-policy produces a new inner policy to be used in the next episode. M-FOS then uses generic model-free optimisation methods to learn meta-policies that accomplish long-horizon opponent shaping. Empirically, M-FOS near-optimally exploits naive learners and other, more sophisticated algorithms from the literature. For example, to the best of our knowledge, it is the first method to learn the well-known Zero-Determinant (ZD) extortion strategy in the IPD. In the same settings, M-FOS leads to socially optimal outcomes under meta-self-play. Finally, we show that M-FOS can be scaled to high-dimensional settings.

Sascha Frey, Kang Li, Peer Nagy et al.

Financial exchanges across the world use limit order books (LOBs) to process orders and match trades. For research purposes it is important to have large scale efficient simulators of LOB dynamics. LOB simulators have previously been implemented in the context of agent-based models (ABMs), reinforcement learning (RL) environments, and generative models, processing order flows from historical data sets and hand-crafted agents alike. For many applications, there is a requirement for processing multiple books, either for the calibration of ABMs or for the training of RL agents. We showcase the first GPU-enabled LOB simulator designed to process thousands of books in parallel, with a notably reduced per-message processing time. The implementation of our simulator - JAX-LOB - is based on design choices that aim to best exploit the powers of JAX without compromising on the realism of LOB-related mechanisms. We integrate JAX-LOB with other JAX packages, to provide an example of how one may address an optimal execution problem with reinforcement learning, and to share some preliminary results from end-to-end RL training on GPUs.

Chris Lu, Timon Willi, Alistair Letcher et al.

Adversarial attacks in reinforcement learning (RL) often assume highly-privileged access to the victim's parameters, environment, or data. Instead, this paper proposes a novel adversarial setting called a Cheap Talk MDP in which an Adversary can merely append deterministic messages to the Victim's observation, resulting in a minimal range of influence. The Adversary cannot occlude ground truth, influence underlying environment dynamics or reward signals, introduce non-stationarity, add stochasticity, see the Victim's actions, or access their parameters. Additionally, we present a simple meta-learning algorithm called Adversarial Cheap Talk (ACT) to train Adversaries in this setting. We demonstrate that an Adversary trained with ACT still significantly influences the Victim's training and testing performance, despite the highly constrained setting. Affecting train-time performance reveals a new attack vector and provides insight into the success and failure modes of existing RL algorithms. More specifically, we show that an ACT Adversary is capable of harming performance by interfering with the learner's function approximation, or instead helping the Victim's performance by outputting useful features. Finally, we show that an ACT Adversary can manipulate messages during train-time to directly and arbitrarily control the Victim at test-time. Project video and code are available at https://sites.google.com/view/adversarial-cheap-talk

Kaiwen Cai, Chris Xiaoxuan Lu, Xiaowei Huang

Place recognition is key to Simultaneous Localization and Mapping (SLAM) and spatial perception. However, a place recognition in the wild often suffers from erroneous predictions due to image variations, e.g., changing viewpoints and street appearance. Integrating uncertainty estimation into the life cycle of place recognition is a promising method to mitigate the impact of variations on place recognition performance. However, existing uncertainty estimation approaches in this vein are either computationally inefficient (e.g., Monte Carlo dropout) or at the cost of dropped accuracy. This paper proposes STUN, a self-teaching framework that learns to simultaneously predict the place and estimate the prediction uncertainty given an input image. To this end, we first train a teacher net using a standard metric learning pipeline to produce embedding priors. Then, supervised by the pretrained teacher net, a student net with an additional variance branch is trained to finetune the embedding priors and estimate the uncertainty sample by sample. During the online inference phase, we only use the student net to generate a place prediction in conjunction with the uncertainty. When compared with place recognition systems that are ignorant to the uncertainty, our framework features the uncertainty estimation for free without sacrificing any prediction accuracy. Our experimental results on the large-scale Pittsburgh30k dataset demonstrate that STUN outperforms the state-of-the-art methods in both recognition accuracy and the quality of uncertainty estimation.

Jianning Deng, Gabriel Chan, Hantao Zhong et al.

This paper presents a novel framework for robust 3D object detection from point clouds via cross-modal hallucination. Our proposed approach is agnostic to either hallucination direction between LiDAR and 4D radar. We introduce multiple alignments on both spatial and feature levels to achieve simultaneous backbone refinement and hallucination generation. Specifically, spatial alignment is proposed to deal with the geometry discrepancy for better instance matching between LiDAR and radar. The feature alignment step further bridges the intrinsic attribute gap between the sensing modalities and stabilizes the training. The trained object detection models can deal with difficult detection cases better, even though only single-modal data is used as the input during the inference stage. Extensive experiments on the View-of-Delft (VoD) dataset show that our proposed method outperforms the state-of-the-art (SOTA) methods for both radar and LiDAR object detection while maintaining competitive efficiency in runtime. Code is available at https://github.com/DJNing/See_beyond_seeing.

Kaiwen Cai, Qiyue Xia, Peize Li et al.

The majority of human detection methods rely on the sensor using visible lights (e.g., RGB cameras) but such sensors are limited in scenarios with degraded vision conditions. In this paper, we present a multimodal human detection system that combines portable thermal cameras and single-chip mmWave radars. To mitigate the noisy detection features caused by the low contrast of thermal cameras and the multi-path noise of radar point clouds, we propose a Bayesian feature extractor and a novel uncertainty-guided fusion method that surpasses a variety of competing methods, either single-modal or multi-modal. We evaluate the proposed method on real-world data collection and demonstrate that our approach outperforms the state-of-the-art methods by a large margin.

Chris Lu, Sebastian Towers, Jakob Foerster

Meta-learning, the notion of learning to learn, enables learning systems to quickly and flexibly solve new tasks. This usually involves defining a set of outer-loop meta-parameters that are then used to update a set of inner-loop parameters. Most meta-learning approaches use complicated and computationally expensive bi-level optimisation schemes to update these meta-parameters. Ideally, systems should perform multiple orders of meta-learning, i.e. to learn to learn to learn and so on, to accelerate their own learning. Unfortunately, standard meta-learning techniques are often inappropriate for these higher-order meta-parameters because the meta-optimisation procedure becomes too complicated or unstable. Inspired by the higher-order meta-learning we observe in real-world evolution, we show that using simple population-based evolution implicitly optimises for arbitrarily-high order meta-parameters. First, we theoretically prove and empirically show that population-based evolution implicitly optimises meta-parameters of arbitrarily-high order in a simple setting. We then introduce a minimal self-referential parameterisation, which in principle enables arbitrary-order meta-learning. Finally, we show that higher-order meta-learning improves performance on time series forecasting tasks.

Nikolaos Tsagkas, Andreas Sochopoulos, Duolikun Danier et al.

The adoption of pre-trained visual representations (PVRs), leveraging features from large-scale vision models, has become a popular paradigm for training visuomotor policies. However, these powerful representations can encode a broad range of task-irrelevant scene information, making the resulting trained policies vulnerable to out-of-domain visual changes and distractors. In this work we address visuomotor policy feature pooling as a solution to the observed lack of robustness in perturbed scenes. We achieve this via Attentive Feature Aggregation (AFA), a lightweight, trainable pooling mechanism that learns to naturally attend to task-relevant visual cues, ignoring even semantically rich scene distractors. Through extensive experiments in both simulation and the real world, we demonstrate that policies trained with AFA significantly outperform standard pooling approaches in the presence of visual perturbations, without requiring expensive dataset augmentation or fine-tuning of the PVR. Our findings show that ignoring extraneous visual information is a crucial step towards deploying robust and generalisable visuomotor policies. Project Page: tsagkas.github.io/afa

Kaiwen Cai, Chris Xiaoxuan Lu, Xiaowei Huang

Dense prediction tasks are common for 3D point clouds, but the uncertainties inherent in massive points and their embeddings have long been ignored. In this work, we present CUE, a novel uncertainty estimation method for dense prediction tasks in 3D point clouds. Inspired by metric learning, the key idea of CUE is to explore cross-point embeddings upon a conventional 3D dense prediction pipeline. Specifically, CUE involves building a probabilistic embedding model and then enforcing metric alignments of massive points in the embedding space. We also propose CUE+, which enhances CUE by explicitly modeling crosspoint dependencies in the covariance matrix. We demonstrate that both CUE and CUE+ are generic and effective for uncertainty estimation in 3D point clouds with two different tasks: (1) in 3D geometric feature learning we for the first time obtain wellcalibrated uncertainty, and (2) in semantic segmentation we reduce uncertainty's Expected Calibration Error of the state-of-the-arts by 16.5%. All uncertainties are estimated without compromising predictive performance.

Kaiwen Cai, Chris Xiaoxuan Lu, Xingyu Zhao et al.

Most image retrieval research prioritizes improving predictive performance, often overlooking situations where the reliability of predictions is equally important. The gap between model performance and reliability requirements highlights the need for a systematic approach to analyze and address the risks associated with image retrieval. Uncertainty quantification technique can be applied to mitigate this issue by assessing uncertainty for retrieval sets, but it provides only a heuristic estimate of uncertainty rather than a guarantee. To address these limitations, we present Risk Controlled Image Retrieval (RCIR), which generates retrieval sets with coverage guarantee, i.e., retrieval sets that are guaranteed to contain the true nearest neighbors with a predefined probability. RCIR can be easily integrated with existing uncertainty-aware image retrieval systems, agnostic to data distribution and model selection. To the best of our knowledge, this is the first work that provides coverage guarantees to image retrieval. The validity and efficiency of RCIR are demonstrated on four real-world datasets: CAR-196, CUB-200, Pittsburgh, and ChestX-Det.

Eduardo Pignatelli, Jarek Liesen, Robert Tjarko Lange et al.

As Deep Reinforcement Learning (Deep RL) research moves towards solving large-scale worlds, efficient environment simulations become crucial for rapid experimentation. However, most existing environments struggle to scale to high throughput, setting back meaningful progress. Interactions are typically computed on the CPU, limiting training speed and throughput, due to slower computation and communication overhead when distributing the task across multiple machines. Ultimately, Deep RL training is CPU-bound, and developing batched, fast, and scalable environments has become a frontier for progress. Among the most used Reinforcement Learning (RL) environments, MiniGrid is at the foundation of several studies on exploration, curriculum learning, representation learning, diversity, meta-learning, credit assignment, and language-conditioned RL, and still suffers from the limitations described above. In this work, we introduce NAVIX, a re-implementation of MiniGrid in JAX. NAVIX achieves over 200 000x speed improvements in batch mode, supporting up to 2048 agents in parallel on a single Nvidia A100 80 GB. This reduces experiment times from one week to 15 minutes, promoting faster design iterations and more scalable RL model development.

Xingyu Chen, Xinyu Zhang, Qiyue Xia et al.

Millimeter wave (mmWave) sensing is an emerging technology with applications in 3D object characterization and environment mapping. However, realizing precise 3D reconstruction from sparse mmWave signals remains challenging. Existing methods rely on data-driven learning, constrained by dataset availability and difficulty in generalization. We propose DiffSBR, a differentiable framework for mmWave-based 3D reconstruction. DiffSBR incorporates a differentiable ray tracing engine to simulate radar point clouds from virtual 3D models. A gradient-based optimizer refines the model parameters to minimize the discrepancy between simulated and real point clouds. Experiments using various radar hardware validate DiffSBR's capability for fine-grained 3D reconstruction, even for novel objects unseen by the radar previously. By integrating physics-based simulation with gradient optimization, DiffSBR transcends the limitations of data-driven approaches and pioneers a new paradigm for mmWave sensing.

Zhaoguang Yi, Xiangyu Wen, Qiyue Xia et al.

Indoor Positioning Systems (IPS) traditionally rely on odometry and building infrastructures like WiFi, often supplemented by building floor plans for increased accuracy. However, the limitation of floor plans in terms of availability and timeliness of updates challenges their wide applicability. In contrast, the proliferation of smartphones and WiFi-enabled robots has made crowdsourced radio maps - databases pairing locations with their corresponding Received Signal Strengths (RSS) - increasingly accessible. These radio maps not only provide WiFi fingerprint-location pairs but encode movement regularities akin to the constraints imposed by floor plans. This work investigates the possibility of leveraging these radio maps as a substitute for floor plans in multimodal IPS. We introduce a new framework to address the challenges of radio map inaccuracies and sparse coverage. Our proposed system integrates an uncertainty-aware neural network model for WiFi localization and a bespoken Bayesian fusion technique for optimal fusion. Extensive evaluations on multiple real-world sites indicate a significant performance enhancement, with results showing ~ 25% improvement over the best baseline

Bing Wang, Changhao Chen, Chris Xiaoxuan Lu et al.

Deep learning has achieved impressive results in camera localization, but current single-image techniques typically suffer from a lack of robustness, leading to large outliers. To some extent, this has been tackled by sequential (multi-images) or geometry constraint approaches, which can learn to reject dynamic objects and illumination conditions to achieve better performance. In this work, we show that attention can be used to force the network to focus on more geometrically robust objects and features, achieving state-of-the-art performance in common benchmark, even if using only a single image as input. Extensive experimental evidence is provided through public indoor and outdoor datasets. Through visualization of the saliency maps, we demonstrate how the network learns to reject dynamic objects, yielding superior global camera pose regression performance. The source code is avaliable at https://github.com/BingCS/AtLoc.

Xingyu Chen, Xinyu Zhang, Kai Zheng et al.

Digital twins, virtual simulated replicas of physical scenes, are transforming system design across industries. However, their potential in radio frequency (RF) systems has been limited by the non-differentiable nature of conventional RF simulators. The visibility of propagation paths causes severe discontinuities, and differentiable rendering techniques from computer graphics cannot easily transfer due to point-source antennas and dominant specular reflections. In this paper, we present RFDT, a physically based differentiable RF simulation framework that enables gradient-based interaction between virtual and physical worlds. RFDT resolves discontinuities with a physically grounded edge-diffraction transition function, and mitigates non-convexity from Fourier-domain processing through a signal domain transform surrogate. Our implementation demonstrates RFDT's ability to accurately reconstruct digital twins from real RF measurements. Moreover, RFDT can augment diverse downstream applications, such as test-time adaptation of machine learning-based RF sensing and physically constrained optimization of communication systems.

Fangqiang Ding, Xiangyu Wen, Yunzhou Zhu et al.

3D occupancy-based perception pipeline has significantly advanced autonomous driving by capturing detailed scene descriptions and demonstrating strong generalizability across various object categories and shapes. Current methods predominantly rely on LiDAR or camera inputs for 3D occupancy prediction. These methods are susceptible to adverse weather conditions, limiting the all-weather deployment of self-driving cars. To improve perception robustness, we leverage the recent advances in automotive radars and introduce a novel approach that utilizes 4D imaging radar sensors for 3D occupancy prediction. Our method, RadarOcc, circumvents the limitations of sparse radar point clouds by directly processing the 4D radar tensor, thus preserving essential scene details. RadarOcc innovatively addresses the challenges associated with the voluminous and noisy 4D radar data by employing Doppler bins descriptors, sidelobe-aware spatial sparsification, and range-wise self-attention mechanisms. To minimize the interpolation errors associated with direct coordinate transformations, we also devise a spherical-based feature encoding followed by spherical-to-Cartesian feature aggregation. We benchmark various baseline methods based on distinct modalities on the public K-Radar dataset. The results demonstrate RadarOcc's state-of-the-art performance in radar-based 3D occupancy prediction and promising results even when compared with LiDAR- or camera-based methods. Additionally, we present qualitative evidence of the superior performance of 4D radar in adverse weather conditions and explore the impact of key pipeline components through ablation studies.

Matthew Thomas Jackson, Chris Lu, Louis Kirsch et al.

Recent advancements in meta-learning have enabled the automatic discovery of novel reinforcement learning algorithms parameterized by surrogate objective functions. To improve upon manually designed algorithms, the parameterization of this learned objective function must be expressive enough to represent novel principles of learning (instead of merely recovering already established ones) while still generalizing to a wide range of settings outside of its meta-training distribution. However, existing methods focus on discovering objective functions that, like many widely used objective functions in reinforcement learning, do not take into account the total number of steps allowed for training, or "training horizon". In contrast, humans use a plethora of different learning objectives across the course of acquiring a new ability. For instance, students may alter their studying techniques based on the proximity to exam deadlines and their self-assessed capabilities. This paper contends that ignoring the optimization time horizon significantly restricts the expressive potential of discovered learning algorithms. We propose a simple augmentation to two existing objective discovery approaches that allows the discovered algorithm to dynamically update its objective function throughout the agent's training procedure, resulting in expressive schedules and increased generalization across different training horizons. In the process, we find that commonly used meta-gradient approaches fail to discover such adaptive objective functions while evolution strategies discover highly dynamic learning rules. We demonstrate the effectiveness of our approach on a wide range of tasks and analyze the resulting learned algorithms, which we find effectively balance exploration and exploitation by modifying the structure of their learning rules throughout the agent's lifetime.

Akarsh Kumar, Chris Lu, Louis Kirsch et al.

With the recent Nobel Prize awarded for radical advances in protein discovery, foundation models (FMs) for exploring large combinatorial spaces promise to revolutionize many scientific fields. Artificial Life (ALife) has not yet integrated FMs, thus presenting a major opportunity for the field to alleviate the historical burden of relying chiefly on manual design and trial-and-error to discover the configurations of lifelike simulations. This paper presents, for the first time, a successful realization of this opportunity using vision-language FMs. The proposed approach, called Automated Search for Artificial Life (ASAL), (1) finds simulations that produce target phenomena, (2) discovers simulations that generate temporally open-ended novelty, and (3) illuminates an entire space of interestingly diverse simulations. Because of the generality of FMs, ASAL works effectively across a diverse range of ALife substrates including Boids, Particle Life, Game of Life, Lenia, and Neural Cellular Automata. A major result highlighting the potential of this technique is the discovery of previously unseen Lenia and Boids lifeforms, as well as cellular automata that are open-ended like Conway's Game of Life. Additionally, the use of FMs allows for the quantification of previously qualitative phenomena in a human-aligned way. This new paradigm promises to accelerate ALife research beyond what is possible through human ingenuity alone.

Akbir Khan, Timon Willi, Newton Kwan et al.

In multi-agent settings with mixed incentives, methods developed for zero-sum games have been shown to lead to detrimental outcomes. To address this issue, opponent shaping (OS) methods explicitly learn to influence the learning dynamics of co-players and empirically lead to improved individual and collective outcomes. However, OS methods have only been evaluated in low-dimensional environments due to the challenges associated with estimating higher-order derivatives or scaling model-free meta-learning. Alternative methods that scale to more complex settings either converge to undesirable solutions or rely on unrealistic assumptions about the environment or co-players. In this paper, we successfully scale an OS-based approach to general-sum games with temporally-extended actions and long-time horizons for the first time. After analysing the representations of the meta-state and history used by previous algorithms, we propose a simplified version called Shaper. We show empirically that Shaper leads to improved individual and collective outcomes in a range of challenging settings from literature. We further formalize a technique previously implicit in the literature, and analyse its contribution to opponent shaping. We show empirically that this technique is helpful for the functioning of prior methods in certain environments. Lastly, we show that previous environments, such as the CoinGame, are inadequate for analysing temporally-extended general-sum interactions.

Nikolaos Tsagkas, Jack Rome, Subramanian Ramamoorthy et al.

Precise manipulation that is generalizable across scenes and objects remains a persistent challenge in robotics. Current approaches for this task heavily depend on having a significant number of training instances to handle objects with pronounced visual and/or geometric part ambiguities. Our work explores the grounding of fine-grained part descriptors for precise manipulation in a zero-shot setting by utilizing web-trained text-to-image diffusion-based generative models. We tackle the problem by framing it as a dense semantic part correspondence task. Our model returns a gripper pose for manipulating a specific part, using as reference a user-defined click from a source image of a visually different instance of the same object. We require no manual grasping demonstrations as we leverage the intrinsic object geometry and features. Practical experiments in a real-world tabletop scenario validate the efficacy of our approach, demonstrating its potential for advancing semantic-aware robotics manipulation. Web page: https://tsagkas.github.io/click2grasp

Kaiwen Cai, Zhekai Duan, Gaowen Liu et al.

Recent advancements in Vision-Language (VL) models have sparked interest in their deployment on edge devices, yet challenges in handling diverse visual modalities, manual annotation, and computational constraints remain. We introduce EdgeVL, a novel framework that bridges this gap by seamlessly integrating dual-modality knowledge distillation and quantization-aware contrastive learning. This approach enables the adaptation of large VL models, like CLIP, for efficient use with both RGB and non-RGB images on resource-limited devices without the need for manual annotations. EdgeVL not only transfers visual language alignment capabilities to compact models but also maintains feature quality post-quantization, significantly enhancing open-vocabulary classification performance across various visual modalities. Our work represents the first systematic effort to adapt large VL models for edge deployment, showcasing up to 15.4% accuracy improvements on multiple datasets and up to 93-fold reduction in model size.

Steven Morad, Chris Lu, Ryan Kortvelesy et al.

Memory models such as Recurrent Neural Networks (RNNs) and Transformers address Partially Observable Markov Decision Processes (POMDPs) by mapping trajectories to latent Markov states. Neither model scales particularly well to long sequences, especially compared to an emerging class of memory models called Linear Recurrent Models. We discover that the recurrent update of these models resembles a monoid, leading us to reformulate existing models using a novel monoid-based framework that we call memoroids. We revisit the traditional approach to batching in recurrent reinforcement learning, highlighting theoretical and empirical deficiencies. We leverage memoroids to propose a batching method that improves sample efficiency, increases the return, and simplifies the implementation of recurrent loss functions in reinforcement learning.

Alexandra Souly, Timon Willi, Akbir Khan et al.

Reinforcement learning solutions have great success in the 2-player general sum setting. In this setting, the paradigm of Opponent Shaping (OS), in which agents account for the learning of their co-players, has led to agents which are able to avoid collectively bad outcomes, whilst also maximizing their reward. These methods have currently been limited to 2-player game. However, the real world involves interactions with many more agents, with interactions on both local and global scales. In this paper, we extend Opponent Shaping (OS) methods to environments involving multiple co-players and multiple shaping agents. We evaluate on over 4 different environments, varying the number of players from 3 to 5, and demonstrate that model-based OS methods converge to equilibrium with better global welfare than naive learning. However, we find that when playing with a large number of co-players, OS methods' relative performance reduces, suggesting that in the limit OS methods may not perform well. Finally, we explore scenarios where more than one OS method is present, noticing that within games requiring a majority of cooperating agents, OS methods converge to outcomes with poor global welfare.

Nikolaos Tsagkas, Andreas Sochopoulos, Duolikun Danier et al.

The integration of pre-trained visual representations (PVRs) has significantly advanced visuomotor policy learning. However, effectively leveraging these models remains a challenge. We identify temporal entanglement as a critical, inherent issue when using these time-invariant models in sequential decision-making tasks. This entanglement arises because PVRs, optimised for static image understanding, struggle to represent the temporal dependencies crucial for visuomotor control. In this work, we quantify the impact of temporal entanglement, demonstrating a strong correlation between a policy's success rate and the ability of its latent space to capture task-progression cues. Based on these insights, we propose a simple, yet effective disentanglement baseline designed to mitigate temporal entanglement. Our empirical results show that traditional methods aimed at enriching features with temporal components are insufficient on their own, highlighting the necessity of explicitly addressing temporal disentanglement for robust visuomotor policy learning.

Junqiao Fan, Yunjiao Zhou, Yizhuo Yang et al.

Human mesh reconstruction (HMR) provides direct insights into body-environment interaction, which enables various immersive applications. While existing large-scale HMR datasets rely heavily on line-of-sight RGB input, vision-based sensing is limited by occlusion, lighting variation, and privacy concerns. To overcome these limitations, recent efforts have explored radio-frequency (RF) mmWave radar for privacy-preserving indoor human sensing. However, current radar datasets are constrained by sparse skeleton labels, limited scale, and simple in-place actions. To advance the HMR research community, we introduce M4Human, the current largest-scale (661K-frame) ($9\times$ prior largest) multimodal benchmark, featuring high-resolution mmWave radar, RGB, and depth data. M4Human provides both raw radar tensors (RT) and processed radar point clouds (RPC) to enable research across different levels of RF signal granularity. M4Human includes high-quality motion capture (MoCap) annotations with 3D meshes and global trajectories, and spans 20 subjects and 50 diverse actions, including in-place, sit-in-place, and free-space sports or rehabilitation movements. We establish benchmarks on both RT and RPC modalities, as well as multimodal fusion with RGB-D modalities. Extensive results highlight the significance of M4Human for radar-based human modeling while revealing persistent challenges under fast, unconstrained motion. The dataset and code will be released after the paper publication.

Kezhong Liu, Yiwen Zhou, Mozi Chen et al.

This work proposes a mmWave radar's scene flow estimation framework supervised by data from a widespread visual-inertial (VI) sensor suite, allowing crowdsourced training data from smart vehicles. Current scene flow estimation methods for mmWave radar are typically supervised by dense point clouds from 3D LiDARs, which are expensive and not widely available in smart vehicles. While VI data are more accessible, visual images alone cannot capture the 3D motions of moving objects, making it difficult to supervise their scene flow. Moreover, the temporal drift of VI rigid transformation also degenerates the scene flow estimation of static points. To address these challenges, we propose a drift-free rigid transformation estimator that fuses kinematic model-based ego-motions with neural network-learned results. It provides strong supervision signals to radar-based rigid transformation and infers the scene flow of static points. Then, we develop an optical-mmWave supervision extraction module that extracts the supervision signals of radar rigid transformation and scene flow. It strengthens the supervision by learning the scene flow of dynamic points with the joint constraints of optical and mmWave radar measurements. Extensive experiments demonstrate that, in smoke-filled environments, our method even outperforms state-of-the-art (SOTA) approaches using costly LiDARs.

Andrei Lupu, Chris Lu, Jarek Liesen et al.

Dataset distillation aims to condense large datasets into a small number of synthetic examples that can be used as drop-in replacements when training new models. It has applications to interpretability, neural architecture search, privacy, and continual learning. Despite strong successes in supervised domains, such methods have not yet been extended to reinforcement learning, where the lack of a fixed dataset renders most distillation methods unusable. Filling the gap, we formalize behaviour distillation, a setting that aims to discover and then condense the information required for training an expert policy into a synthetic dataset of state-action pairs, without access to expert data. We then introduce Hallucinating Datasets with Evolution Strategies (HaDES), a method for behaviour distillation that can discover datasets of just four state-action pairs which, under supervised learning, train agents to competitive performance levels in continuous control tasks. We show that these datasets generalize out of distribution to training policies with a wide range of architectures and hyperparameters. We also demonstrate application to a downstream task, namely training multi-task agents in a zero-shot fashion. Beyond behaviour distillation, HaDES provides significant improvements in neuroevolution for RL over previous approaches and achieves SoTA results on one standard supervised dataset distillation task. Finally, we show that visualizing the synthetic datasets can provide human-interpretable task insights.

Jarek Liesen, Chris Lu, Andrei Lupu et al.

Reinforcement learning (RL) agents are commonly trained and evaluated in the same environment. In contrast, humans often train in a specialized environment before being evaluated, such as studying a book before taking an exam. The potential of such specialized training environments is still vastly underexplored, despite their capacity to dramatically speed up training. The framework of synthetic environments takes a first step in this direction by meta-learning neural network-based Markov decision processes (MDPs). The initial approach was limited to toy problems and produced environments that did not transfer to unseen RL algorithms. We extend this approach in three ways: Firstly, we modify the meta-learning algorithm to discover environments invariant towards hyperparameter configurations and learning algorithms. Secondly, by leveraging hardware parallelism and introducing a curriculum on an agent's evaluation episode horizon, we can achieve competitive results on several challenging continuous control problems. Thirdly, we surprisingly find that contextual bandits enable training RL agents that transfer well to their evaluation environment, even if it is a complex MDP. Hence, we set up our experiments to train synthetic contextual bandits, which perform on par with synthetic MDPs, yield additional insights into the evaluation environment, and can speed up downstream applications.

Jonathan Cook, Chris Lu, Edward Hughes et al.

Cultural accumulation drives the open-ended and diverse progress in capabilities spanning human history. It builds an expanding body of knowledge and skills by combining individual exploration with inter-generational information transmission. Despite its widespread success among humans, the capacity for artificial learning agents to accumulate culture remains under-explored. In particular, approaches to reinforcement learning typically strive for improvements over only a single lifetime. Generational algorithms that do exist fail to capture the open-ended, emergent nature of cultural accumulation, which allows individuals to trade-off innovation and imitation. Building on the previously demonstrated ability for reinforcement learning agents to perform social learning, we find that training setups which balance this with independent learning give rise to cultural accumulation. These accumulating agents outperform those trained for a single lifetime with the same cumulative experience. We explore this accumulation by constructing two models under two distinct notions of a generation: episodic generations, in which accumulation occurs via in-context learning and train-time generations, in which accumulation occurs via in-weights learning. In-context and in-weights cultural accumulation can be interpreted as analogous to knowledge and skill accumulation, respectively. To the best of our knowledge, this work is the first to present general models that achieve emergent cultural accumulation in reinforcement learning, opening up new avenues towards more open-ended learning systems, as well as presenting new opportunities for modelling human culture.

Fangqiang Ding, Yunzhou Zhu, Xiangyu Wen et al.

Designing egocentric 3D hand pose estimation systems that can perform reliably in complex, real-world scenarios is crucial for downstream applications. Previous approaches using RGB or NIR imagery struggle in challenging conditions: RGB methods are susceptible to lighting variations and obstructions like handwear, while NIR techniques can be disrupted by sunlight or interference from other NIR-equipped devices. To address these limitations, we present ThermoHands, the first benchmark focused on thermal image-based egocentric 3D hand pose estimation, demonstrating the potential of thermal imaging to achieve robust performance under these conditions. The benchmark includes a multi-view and multi-spectral dataset collected from 28 subjects performing hand-object and hand-virtual interactions under diverse scenarios, accurately annotated with 3D hand poses through an automated process. We introduce a new baseline method, TherFormer, utilizing dual transformer modules for effective egocentric 3D hand pose estimation in thermal imagery. Our experimental results highlight TherFormer's leading performance and affirm thermal imaging's effectiveness in enabling robust 3D hand pose estimation in adverse conditions.

Kitty Fung, Qizhen Zhang, Chris Lu et al.

Learning in general-sum games often yields collectively sub-optimal results. Addressing this, opponent shaping (OS) methods actively guide the learning processes of other agents, empirically leading to improved individual and group performances in many settings. Early OS methods use higher-order derivatives to shape the learning of co-players, making them unsuitable for shaping multiple learning steps. Follow-up work, Model-free Opponent Shaping (M-FOS), addresses these by reframing the OS problem as a meta-game. In contrast to early OS methods, there is little theoretical understanding of the M-FOS framework. Providing theoretical guarantees for M-FOS is hard because A) there is little literature on theoretical sample complexity bounds for meta-reinforcement learning B) M-FOS operates in continuous state and action spaces, so theoretical analysis is challenging. In this work, we present R-FOS, a tabular version of M-FOS that is more suitable for theoretical analysis. R-FOS discretises the continuous meta-game MDP into a tabular MDP. Within this discretised MDP, we adapt the $R_{max}$ algorithm, most prominently used to derive PAC-bounds for MDPs, as the meta-learner in the R-FOS algorithm. We derive a sample complexity bound that is exponential in the cardinality of the inner state and action space and the number of agents. Our bound guarantees that, with high probability, the final policy learned by an R-FOS agent is close to the optimal policy, apart from a constant factor. Finally, we investigate how R-FOS's sample complexity scales in the size of state-action space. Our theoretical results on scaling are supported empirically in the Matching Pennies environment.

Nikolaos Tsagkas, Oisin Mac Aodha, Chris Xiaoxuan Lu

We present Visual-Language Fields (VL-Fields), a neural implicit spatial representation that enables open-vocabulary semantic queries. Our model encodes and fuses the geometry of a scene with vision-language trained latent features by distilling information from a language-driven segmentation model. VL-Fields is trained without requiring any prior knowledge of the scene object classes, which makes it a promising representation for the field of robotics. Our model outperformed the similar CLIP-Fields model in the task of semantic segmentation by almost 10%.