Tao Chen

Tao Chen, Megha Tippur, Siyang Wu et al. · deepmind

In-hand object reorientation is necessary for performing many dexterous manipulation tasks, such as tool use in less structured environments that remain beyond the reach of current robots. Prior works built reorientation systems assuming one or many of the following: reorienting only specific objects with simple shapes, limited range of reorientation, slow or quasistatic manipulation, simulation-only results, the need for specialized and costly sensor suites, and other constraints which make the system infeasible for real-world deployment. We present a general object reorientation controller that does not make these assumptions. It uses readings from a single commodity depth camera to dynamically reorient complex and new object shapes by any rotation in real-time, with the median reorientation time being close to seven seconds. The controller is trained using reinforcement learning in simulation and evaluated in the real world on new object shapes not used for training, including the most challenging scenario of reorienting objects held in the air by a downward-facing hand that must counteract gravity during reorientation. Our hardware platform only uses open-source components that cost less than five thousand dollars. Although we demonstrate the ability to overcome assumptions in prior work, there is ample scope for improving absolute performance. For instance, the challenging duck-shaped object not used for training was dropped in 56 percent of the trials. When it was not dropped, our controller reoriented the object within 0.4 radians (23 degrees) 75 percent of the time. Videos are available at: https://taochenshh.github.io/projects/visual-dexterity.

Yu-Wei Chao, Chris Paxton, Yu Xiang et al. · nvidia

We introduce a new simulation benchmark "HandoverSim" for human-to-robot object handovers. To simulate the giver's motion, we leverage a recent motion capture dataset of hand grasping of objects. We create training and evaluation environments for the receiver with standardized protocols and metrics. We analyze the performance of a set of baselines and show a correlation with a real-world evaluation. Code is open sourced at https://handover-sim.github.io.

Zhehui Huang, Sumeet Batra, Tao Chen et al.

Reinforcement learning (RL) has shown promise in creating robust policies for robotics tasks. However, contemporary RL algorithms are data-hungry, often requiring billions of environment transitions to train successful policies. This necessitates the use of fast and highly-parallelizable simulators. In addition to speed, such simulators need to model the physics of the robots and their interaction with the environment to a level acceptable for transferring policies learned in simulation to reality. We present QuadSwarm, a fast, reliable simulator for research in single and multi-robot RL for quadrotors that addresses both issues. QuadSwarm, with fast forward-dynamics propagation decoupled from rendering, is designed to be highly parallelizable such that throughput scales linearly with additional compute. It provides multiple components tailored toward multi-robot RL, including diverse training scenarios, and provides domain randomization to facilitate the development and sim2real transfer of multi-quadrotor control policies. Initial experiments suggest that QuadSwarm achieves over 48,500 simulation samples per second (SPS) on a single quadrotor and over 62,000 SPS on eight quadrotors on a 16-core CPU. The code can be found in https://github.com/Zhehui-Huang/quad-swarm-rl.

Kai Hui, Honglei Zhuang, Tao Chen et al. · deepmind

State-of-the-art neural models typically encode document-query pairs using cross-attention for re-ranking. To this end, models generally utilize an encoder-only (like BERT) paradigm or an encoder-decoder (like T5) approach. These paradigms, however, are not without flaws, i.e., running the model on all query-document pairs at inference-time incurs a significant computational cost. This paper proposes a new training and inference paradigm for re-ranking. We propose to finetune a pretrained encoder-decoder model using in the form of document to query generation. Subsequently, we show that this encoder-decoder architecture can be decomposed into a decoder-only language model during inference. This results in significant inference time speedups since the decoder-only architecture only needs to learn to interpret static encoder embeddings during inference. Our experiments show that this new paradigm achieves results that are comparable to the more expensive cross-attention ranking approaches while being up to 6.8X faster. We believe this work paves the way for more efficient neural rankers that leverage large pretrained models.

Marcel Torne, Max Balsells, Zihan Wang et al. · deepmind

Exploration and reward specification are fundamental and intertwined challenges for reinforcement learning. Solving sequential decision-making tasks requiring expansive exploration requires either careful design of reward functions or the use of novelty-seeking exploration bonuses. Human supervisors can provide effective guidance in the loop to direct the exploration process, but prior methods to leverage this guidance require constant synchronous high-quality human feedback, which is expensive and impractical to obtain. In this work, we present a technique called Human Guided Exploration (HuGE), which uses low-quality feedback from non-expert users that may be sporadic, asynchronous, and noisy. HuGE guides exploration for reinforcement learning not only in simulation but also in the real world, all without meticulous reward specification. The key concept involves bifurcating human feedback and policy learning: human feedback steers exploration, while self-supervised learning from the exploration data yields unbiased policies. This procedure can leverage noisy, asynchronous human feedback to learn policies with no hand-crafted reward design or exploration bonuses. HuGE is able to learn a variety of challenging multi-stage robotic navigation and manipulation tasks in simulation using crowdsourced feedback from non-expert users. Moreover, this paradigm can be scaled to learning directly on real-world robots, using occasional, asynchronous feedback from human supervisors.

Kai Hui, Tao Chen, Zhen Qin et al. · deepmind

Retrieval augmentation has shown promising improvements in different tasks. However, whether such augmentation can assist a large language model based re-ranker remains unclear. We investigate how to augment T5-based re-rankers using high-quality information retrieved from two external corpora -- a commercial web search engine and Wikipedia. We empirically demonstrate how retrieval augmentation can substantially improve the effectiveness of T5-based re-rankers for both in-domain and zero-shot out-of-domain re-ranking tasks.

Sizhe Li, Zhiao Huang, Tao Chen et al.

In this work, we aim to learn dexterous manipulation of deformable objects using multi-fingered hands. Reinforcement learning approaches for dexterous rigid object manipulation would struggle in this setting due to the complexity of physics interaction with deformable objects. At the same time, previous trajectory optimization approaches with differentiable physics for deformable manipulation would suffer from local optima caused by the explosion of contact modes from hand-object interactions. To address these challenges, we propose DexDeform, a principled framework that abstracts dexterous manipulation skills from human demonstration and refines the learned skills with differentiable physics. Concretely, we first collect a small set of human demonstrations using teleoperation. And we then train a skill model using demonstrations for planning over action abstractions in imagination. To explore the goal space, we further apply augmentations to the existing deformable shapes in demonstrations and use a gradient optimizer to refine the actions planned by the skill model. Finally, we adopt the refined trajectories as new demonstrations for finetuning the skill model. To evaluate the effectiveness of our approach, we introduce a suite of six challenging dexterous deformable object manipulation tasks. Compared with baselines, DexDeform is able to better explore and generalize across novel goals unseen in the initial human demonstrations.

Tao Chen, Luxin Liu, Xuepeng Jia et al.

Logical rules, both transferable and explainable, are widely used as weakly supervised signals for many downstream tasks such as named entity tagging. To reduce the human effort of writing rules, previous researchers adopt an iterative approach to automatically learn logical rules from several seed rules. However, obtaining more seed rules can only be accomplished by extra human annotation with heavy costs. Limited by the size and quality of the seed rules, the model performance of previous systems is bounded. In this paper, we develop a novel framework STREAM to distill task-specific logical rules from large pre-trained models. Specifically, we borrow recent prompt-based language models as the knowledge expert to yield initial seed rules, and based on the formed high-quality instance pool that acts as an intermediary role, we keep teaching the expert to fit our task and learning task-specific logical rules. Experiments on three public named entity tagging benchmarks demonstrate the effectiveness of our proposed framework. With several predefined prompt templates, our system has gained significant improvements over previous state-of-the-art methods.

Zechu Li, Tao Chen, Zhang-Wei Hong et al.

Reinforcement learning is time-consuming for complex tasks due to the need for large amounts of training data. Recent advances in GPU-based simulation, such as Isaac Gym, have sped up data collection thousands of times on a commodity GPU. Most prior works used on-policy methods like PPO due to their simplicity and ease of scaling. Off-policy methods are more data efficient but challenging to scale, resulting in a longer wall-clock training time. This paper presents a Parallel $Q$-Learning (PQL) scheme that outperforms PPO in wall-clock time while maintaining superior sample efficiency of off-policy learning. PQL achieves this by parallelizing data collection, policy learning, and value learning. Different from prior works on distributed off-policy learning, such as Apex, our scheme is designed specifically for massively parallel GPU-based simulation and optimized to work on a single workstation. In experiments, we demonstrate that $Q$-learning can be scaled to \textit{tens of thousands of parallel environments} and investigate important factors affecting learning speed. The code is available at https://github.com/Improbable-AI/pql.

Adithyavairavan Murali, Tao Chen, Kalyan Vasudev Alwala et al.

This paper introduces PyRobot, an open-source robotics framework for research and benchmarking. PyRobot is a light-weight, high-level interface on top of ROS that provides a consistent set of hardware independent mid-level APIs to control different robots. PyRobot abstracts away details about low-level controllers and inter-process communication, and allows non-robotics researchers (ML, CV researchers) to focus on building high-level AI applications. PyRobot aims to provide a research ecosystem with convenient access to robotics datasets, algorithm implementations and models that can be used to quickly create a state-of-the-art baseline. We believe PyRobot, when paired up with low-cost robot platforms such as LoCoBot, will reduce the entry barrier into robotics, and democratize robotics. PyRobot is open-source, and can be accessed via https://pyrobot.org.

Zechu Li, Rickmer Krohn, Tao Chen et al.

Deep reinforcement learning (RL) algorithms typically parameterize the policy as a deep network that outputs either a deterministic action or a stochastic one modeled as a Gaussian distribution, hence restricting learning to a single behavioral mode. Meanwhile, diffusion models emerged as a powerful framework for multimodal learning. However, the use of diffusion policies in online RL is hindered by the intractability of policy likelihood approximation, as well as the greedy objective of RL methods that can easily skew the policy to a single mode. This paper presents Deep Diffusion Policy Gradient (DDiffPG), a novel actor-critic algorithm that learns from scratch multimodal policies parameterized as diffusion models while discovering and maintaining versatile behaviors. DDiffPG explores and discovers multiple modes through off-the-shelf unsupervised clustering combined with novelty-based intrinsic motivation. DDiffPG forms a multimodal training batch and utilizes mode-specific Q-learning to mitigate the inherent greediness of the RL objective, ensuring the improvement of the diffusion policy across all modes. Our approach further allows the policy to be conditioned on mode-specific embeddings to explicitly control the learned modes. Empirical studies validate DDiffPG's capability to master multimodal behaviors in complex, high-dimensional continuous control tasks with sparse rewards, also showcasing proof-of-concept dynamic online replanning when navigating mazes with unseen obstacles.

Zhang-Wei Hong, Tao Chen, Yen-Chen Lin et al.

State-of-the-art deep Q-learning methods update Q-values using state transition tuples sampled from the experience replay buffer. This strategy often uniformly and randomly samples or prioritizes data sampling based on measures such as the temporal difference (TD) error. Such sampling strategies can be inefficient at learning Q-function because a state's Q-value depends on the Q-value of successor states. If the data sampling strategy ignores the precision of the Q-value estimate of the next state, it can lead to useless and often incorrect updates to the Q-values. To mitigate this issue, we organize the agent's experience into a graph that explicitly tracks the dependency between Q-values of states. Each edge in the graph represents a transition between two states by executing a single action. We perform value backups via a breadth-first search starting from that expands vertices in the graph starting from the set of terminal states and successively moving backward. We empirically show that our method is substantially more data-efficient than several baselines on a diverse range of goal-reaching tasks. Notably, the proposed method also outperforms baselines that consume more batches of training experience and operates from high-dimensional observational data such as images.

Shuang Li, Xavier Puig, Chris Paxton et al.

Language model (LM) pre-training is useful in many language processing tasks. But can pre-trained LMs be further leveraged for more general machine learning problems? We propose an approach for using LMs to scaffold learning and generalization in general sequential decision-making problems. In this approach, goals and observations are represented as a sequence of embeddings, and a policy network initialized with a pre-trained LM predicts the next action. We demonstrate that this framework enables effective combinatorial generalization across different environments and supervisory modalities. We begin by assuming access to a set of expert demonstrations, and show that initializing policies with LMs and fine-tuning them via behavior cloning improves task completion rates by 43.6% in the VirtualHome environment. Next, we integrate an active data gathering procedure in which agents iteratively interact with the environment, relabel past "failed" experiences with new goals, and update their policies in a self-supervised loop. Active data gathering further improves combinatorial generalization, outperforming the best baseline by 25.1%. Finally, we explain these results by investigating three possible factors underlying the effectiveness of the LM-based policy. We find that sequential input representations (vs. fixed-dimensional feature vectors) and LM-based weight initialization are both important for generalization. Surprisingly, however, the format of the policy inputs encoding (e.g. as a natural language string vs. an arbitrary sequential encoding) has little influence. Together, these results suggest that language modeling induces representations that are useful for modeling not just language, but also goals and plans; these representations can aid learning and generalization even outside of language processing.

Tao Chen, Mingyang Zhang, Jing Lu et al.

The pre-trained language model (eg, BERT) based deep retrieval models achieved superior performance over lexical retrieval models (eg, BM25) in many passage retrieval tasks. However, limited work has been done to generalize a deep retrieval model to other tasks and domains. In this work, we carefully select five datasets, including two in-domain datasets and three out-of-domain datasets with different levels of domain shift, and study the generalization of a deep model in a zero-shot setting. Our findings show that the performance of a deep retrieval model is significantly deteriorated when the target domain is very different from the source domain that the model was trained on. On the contrary, lexical models are more robust across domains. We thus propose a simple yet effective framework to integrate lexical and deep retrieval models. Our experiments demonstrate that these two models are complementary, even when the deep model is weaker in the out-of-domain setting. The hybrid model obtains an average of 20.4% relative gain over the deep retrieval model, and an average of 9.54% over the lexical model in three out-of-domain datasets.

Wei Liu, Huanqin Wu, Wenjing Mu et al.

Generating factual-consistent summaries is a challenging task for abstractive summarization. Previous works mainly encode factual information or perform post-correct/rank after decoding. In this paper, we provide a factual-consistent solution from the perspective of contrastive learning, which is a natural extension of previous works. We propose CO2Sum (Contrastive for Consistency), a contrastive learning scheme that can be easily applied on sequence-to-sequence models for factual-consistent abstractive summarization, proving that the model can be fact-aware without modifying the architecture. CO2Sum applies contrastive learning on the encoder, which can help the model be aware of the factual information contained in the input article, or performs contrastive learning on the decoder, which makes the model to generate factual-correct output summary. What's more, these two schemes are orthogonal and can be combined to further improve faithfulness. Comprehensive experiments on public benchmarks demonstrate that CO2Sum improves the faithfulness on large pre-trained language models and reaches competitive results compared to other strong factual-consistent summarization baselines.

Tao Chen, Jie Xu, Pulkit Agrawal

In-hand object reorientation has been a challenging problem in robotics due to high dimensional actuation space and the frequent change in contact state between the fingers and the objects. We present a simple model-free framework that can learn to reorient objects with both the hand facing upwards and downwards. We demonstrate the capability of reorienting over 2000 geometrically different objects in both cases. The learned policies show strong zero-shot transfer performance on new objects. We provide evidence that these policies are amenable to real-world operation by distilling them to use observations easily available in the real world. The videos of the learned policies are available at: https://taochenshh.github.io/projects/in-hand-reorientation.

Tao Chen, Haizhou Shi, Siliang Tang et al.

The journey of reducing noise from distant supervision (DS) generated training data has been started since the DS was first introduced into the relation extraction (RE) task. For the past decade, researchers apply the multi-instance learning (MIL) framework to find the most reliable feature from a bag of sentences. Although the pattern of MIL bags can greatly reduce DS noise, it fails to represent many other useful sentence features in the datasets. In many cases, these sentence features can only be acquired by extra sentence-level human annotation with heavy costs. Therefore, the performance of distantly supervised RE models is bounded. In this paper, we go beyond typical MIL framework and propose a novel contrastive instance learning (CIL) framework. Specifically, we regard the initial MIL as the relational triple encoder and constraint positive pairs against negative pairs for each instance. Experiments demonstrate the effectiveness of our proposed framework, with significant improvements over the previous methods on NYT10, GDS and KBP.

Joshua Gruenstein, Tao Chen, Neel Doshi et al.

A majority of microrobots are constructed using compliant materials that are difficult to model analytically, limiting the utility of traditional model-based controllers. Challenges in data collection on microrobots and large errors between simulated models and real robots make current model-based learning and sim-to-real transfer methods difficult to apply. We propose a novel framework residual model learning (RML) that leverages approximate models to substantially reduce the sample complexity associated with learning an accurate robot model. We show that using RML, we can learn a model of the Harvard Ambulatory MicroRobot (HAMR) using just 12 seconds of passively collected interaction data. The learned model is accurate enough to be leveraged as "proxy-simulator" for learning walking and turning behaviors using model-free reinforcement learning algorithms. RML provides a general framework for learning from extremely small amounts of interaction data, and our experiments with HAMR clearly demonstrate that RML substantially outperforms existing techniques.

Haisong Zhang, Lemao Liu, Haiyun Jiang et al.

This technique report introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities. Compared to most previous publicly available text understanding systems and tools, TexSmart holds some unique features. First, the NER function of TexSmart supports over 1,000 entity types, while most other public tools typically support several to (at most) dozens of entity types. Second, TexSmart introduces new semantic analysis functions like semantic expansion and deep semantic representation, that are absent in most previous systems. Third, a spectrum of algorithms (from very fast algorithms to those that are relatively slow but more accurate) are implemented for one function in TexSmart, to fulfill the requirements of different academic and industrial applications. The adoption of unsupervised or weakly-supervised algorithms is especially emphasized, with the goal of easily updating our models to include fresh data with less human annotation efforts. The main contents of this report include major functions of TexSmart, algorithms for achieving these functions, how to use the TexSmart toolkit and Web APIs, and evaluation results of some key algorithms.

Ansel MacLaughlin, Tao Chen, Burcu Karagol Ayan et al.

While composing a new document, anything from a news article to an email or essay, authors often utilize direct quotes from a variety of sources. Although an author may know what point they would like to make, selecting an appropriate quote for the specific context may be time-consuming and difficult. We therefore propose a novel context-aware quote recommendation system which utilizes the content an author has already written to generate a ranked list of quotable paragraphs and spans of tokens from a given source document. We approach quote recommendation as a variant of open-domain question answering and adapt the state-of-the-art BERT-based methods from open-QA to our task. We conduct experiments on a collection of speech transcripts and associated news articles, evaluating models' paragraph ranking and span prediction performances. Our experiments confirm the strong performance of BERT-based methods on this task, which outperform bag-of-words and neural ranking baselines by more than 30% relative across all ranking metrics. Qualitative analyses show the difficulty of the paragraph and span recommendation tasks and confirm the quotability of the best BERT model's predictions, even if they are not the true selected quotes from the original news articles.

Artem Molchanov, Tao Chen, Wolfgang Hönig et al.

Quadrotor stabilizing controllers often require careful, model-specific tuning for safe operation. We use reinforcement learning to train policies in simulation that transfer remarkably well to multiple different physical quadrotors. Our policies are low-level, i.e., we map the rotorcrafts' state directly to the motor outputs. The trained control policies are very robust to external disturbances and can withstand harsh initial conditions such as throws. We show how different training methodologies (change of the cost function, modeling of noise, use of domain randomization) might affect flight performance. To the best of our knowledge, this is the first work that demonstrates that a simple neural network can learn a robust stabilizing low-level quadrotor controller (without the use of a stabilizing PD controller) that is shown to generalize to multiple quadrotors.

Tao Chen, Adithyavairavan Murali, Abhinav Gupta

Deep reinforcement learning could be used to learn dexterous robotic policies but it is challenging to transfer them to new robots with vastly different hardware properties. It is also prohibitively expensive to learn a new policy from scratch for each robot hardware due to the high sample complexity of modern state-of-the-art algorithms. We propose a novel approach called \textit{Hardware Conditioned Policies} where we train a universal policy conditioned on a vector representation of robot hardware. We considered robots in simulation with varied dynamics, kinematic structure, kinematic lengths and degrees-of-freedom. First, we use the kinematic structure directly as the hardware encoding and show great zero-shot transfer to completely novel robots not seen during training. For robots with lower zero-shot success rate, we also demonstrate that fine-tuning the policy network is significantly more sample-efficient than training a model from scratch. In tasks where knowing the agent dynamics is important for success, we learn an embedding for robot hardware and show that policies conditioned on the encoding of hardware tend to generalize and transfer well. The code and videos are available on the project webpage: https://sites.google.com/view/robot-transfer-hcp.