Jiachen Li

Jiachen Li, Edwin Zhang, Ming Yin et al. · princeton

Behavior constrained policy optimization has been demonstrated to be a successful paradigm for tackling Offline Reinforcement Learning. By exploiting historical transitions, a policy is trained to maximize a learned value function while constrained by the behavior policy to avoid a significant distributional shift. In this paper, we propose our closed-form policy improvement operators. We make a novel observation that the behavior constraint naturally motivates the use of first-order Taylor approximation, leading to a linear approximation of the policy objective. Additionally, as practical datasets are usually collected by heterogeneous policies, we model the behavior policies as a Gaussian Mixture and overcome the induced optimization difficulties by leveraging the LogSumExp's lower bound and Jensen's Inequality, giving rise to a closed-form policy improvement operator. We instantiate offline RL algorithms with our novel policy improvement operators and empirically demonstrate their effectiveness over state-of-the-art algorithms on the standard D4RL benchmark. Our code is available at https://cfpi-icml23.github.io/.

Fan-Yun Sun, Isaac Kauvar, Ruohan Zhang et al. · stanford

Modeling multi-agent systems requires understanding how agents interact. Such systems are often difficult to model because they can involve a variety of types of interactions that layer together to drive rich social behavioral dynamics. Here we introduce a method for accurately modeling multi-agent systems. We present Interaction Modeling with Multiplex Attention (IMMA), a forward prediction model that uses a multiplex latent graph to represent multiple independent types of interactions and attention to account for relations of different strengths. We also introduce Progressive Layer Training, a training strategy for this architecture. We show that our approach outperforms state-of-the-art models in trajectory forecasting and relation inference, spanning three multi-agent scenarios: social navigation, cooperative task achievement, and team sports. We further demonstrate that our approach can improve zero-shot generalization and allows us to probe how different interactions impact agent behavior.

Jiaqi Han, Wenbing Huang, Hengbo Ma et al.

Graph Neural Networks (GNNs) have become a prevailing tool for learning physical dynamics. However, they still encounter several challenges: 1) Physical laws abide by symmetry, which is a vital inductive bias accounting for model generalization and should be incorporated into the model design. Existing simulators either consider insufficient symmetry, or enforce excessive equivariance in practice when symmetry is partially broken by gravity. 2) Objects in the physical world possess diverse shapes, sizes, and properties, which should be appropriately processed by the model. To tackle these difficulties, we propose a novel backbone, Subequivariant Graph Neural Network, which 1) relaxes equivariance to subequivariance by considering external fields like gravity, where the universal approximation ability holds theoretically; 2) introduces a new subequivariant object-aware message passing for learning physical interactions between multiple objects of various shapes in the particle-based representation; 3) operates in a hierarchical fashion, allowing for modeling long-range and complex interactions. Our model achieves on average over 3% enhancement in contact prediction accuracy across 8 scenarios on Physion and 2X lower rollout MSE on RigidFall compared with state-of-the-art GNN simulators, while exhibiting strong generalization and data efficiency.

Xinyi Wang, Michael Saxon, Jiachen Li et al.

While machine learning models rapidly advance the state-of-the-art on various real-world tasks, out-of-domain (OOD) generalization remains a challenging problem given the vulnerability of these models to spurious correlations. We propose a balanced mini-batch sampling strategy to transform a biased data distribution into a spurious-free balanced distribution, based on the invariance of the underlying causal mechanisms for the data generation process. We argue that the Bayes optimal classifiers trained on such balanced distribution are minimax optimal across a diverse enough environment space. We also provide an identifiability guarantee of the latent variable model of the proposed data generation process, when utilizing enough train environments. Experiments are conducted on DomainBed, demonstrating empirically that our method obtains the best performance across 20 baselines reported on the benchmark.

Jiachen Li, Chuanbo Hua, Jinkyoo Park et al.

While the modeling of pair-wise relations has been widely studied in multi-agent interacting systems, its ability to capture higher-level and larger-scale group-wise activities is limited. In this paper, we propose a group-aware relational reasoning approach (named EvolveHypergraph) with explicit inference of the underlying dynamically evolving relational structures, and we demonstrate its effectiveness for multi-agent trajectory prediction. In addition to the edges between a pair of nodes (i.e., agents), we propose to infer hyperedges that adaptively connect multiple nodes to enable group-aware relational reasoning in an unsupervised manner without fixing the number of hyperedges. The proposed approach infers the dynamically evolving relation graphs and hypergraphs over time to capture the evolution of relations, which are used by the trajectory predictor to obtain future states. Moreover, we propose to regularize the smoothness of the relation evolution and the sparsity of the inferred graphs or hypergraphs, which effectively improves training stability and enhances the explainability of inferred relations. The proposed approach is validated on both synthetic crowd simulations and multiple real-world benchmark datasets. Our approach infers explainable, reasonable group-aware relations and achieves state-of-the-art performance in long-term prediction.

Jiachen Li, Ye Yuan, Hong-Bin Shen

Symbolic Regression (SR) is a type of regression analysis to automatically find the mathematical expression that best fits the data. Currently, SR still basically relies on various searching strategies so that a sample-specific model is required to be optimized for every expression, which significantly limits the model's generalization and efficiency. Inspired by the fact that human beings can infer a mathematical expression based on the curve of it, we propose Symbolic Expression Transformer (SET), a sample-agnostic model from the perspective of computer vision for SR. Specifically, the collected data is represented as images and an image caption model is employed for translating images to symbolic expressions. A large-scale dataset without overlap between training and testing sets in the image domain is released. Our results demonstrate the effectiveness of SET and suggest the promising direction of image-based model for solving the challenging SR problem.

Yuping Wang, Shuo Xing, Cui Can et al.

Generative Artificial Intelligence (GenAI) constitutes a transformative technological wave that reconfigures industries through its unparalleled capabilities for content creation, reasoning, planning, and multimodal understanding. This revolutionary force offers the most promising path yet toward solving one of engineering's grandest challenges: achieving reliable, fully autonomous driving, particularly the pursuit of Level 5 autonomy. This survey delivers a comprehensive and critical synthesis of the emerging role of GenAI across the autonomous driving stack. We begin by distilling the principles and trade-offs of modern generative modeling, encompassing VAEs, GANs, Diffusion Models, and Large Language Models (LLMs). We then map their frontier applications in image, LiDAR, trajectory, occupancy, video generation as well as LLM-guided reasoning and decision making. We categorize practical applications, such as synthetic data workflows, end-to-end driving strategies, high-fidelity digital twin systems, smart transportation networks, and cross-domain transfer to embodied AI. We identify key obstacles and possibilities such as comprehensive generalization across rare cases, evaluation and safety checks, budget-limited implementation, regulatory compliance, ethical concerns, and environmental effects, while proposing research plans across theoretical assurances, trust metrics, transport integration, and socio-technical influence. By unifying these threads, the survey provides a forward-looking reference for researchers, engineers, and policymakers navigating the convergence of generative AI and advanced autonomous mobility. An actively maintained repository of cited works is available at https://github.com/taco-group/GenAI4AD.

Jiachen Li, Weixi Feng, Wenhu Chen et al.

Latent Consistency Distillation (LCD) has emerged as a promising paradigm for efficient text-to-image synthesis. By distilling a latent consistency model (LCM) from a pre-trained teacher latent diffusion model (LDM), LCD facilitates the generation of high-fidelity images within merely 2 to 4 inference steps. However, the LCM's efficient inference is obtained at the cost of the sample quality. In this paper, we propose compensating the quality loss by aligning LCM's output with human preference during training. Specifically, we introduce Reward Guided LCD (RG-LCD), which integrates feedback from a reward model (RM) into the LCD process by augmenting the original LCD loss with the objective of maximizing the reward associated with LCM's single-step generation. As validated through human evaluation, when trained with the feedback of a good RM, the 2-step generations from our RG-LCM are favored by humans over the 50-step DDIM samples from the teacher LDM, representing a 25-time inference acceleration without quality loss. As directly optimizing towards differentiable RMs can suffer from over-optimization, we take the initial step to overcome this difficulty by proposing the use of a latent proxy RM (LRM). This novel component serves as an intermediary, connecting our LCM with the RM. Empirically, we demonstrate that incorporating the LRM into our RG-LCD successfully avoids high-frequency noise in the generated images, contributing to both improved Fréchet Inception Distance (FID) on MS-COCO and a higher HPSv2.1 score on HPSv2's test set, surpassing those achieved by the baseline LCM.

Akshat Choube, Rahul Majethia, Sohini Bhattacharya et al.

Longitudinal passive sensing studies for health and behavior outcomes often have missing and incomplete data. Handling missing data effectively is thus a critical data processing and modeling step. Our formative interviews with researchers working in longitudinal health and behavior passive sensing revealed a recurring theme: most researchers consider imputation a low-priority step in their analysis and inference pipeline, opting to use simple and off-the-shelf imputation strategies without comprehensively evaluating its impact on study outcomes. Through this paper, we call attention to the importance of imputation. Using publicly available passive sensing datasets for depression, we show that prioritizing imputation can significantly impact the study outcomes -- with our proposed imputation strategies resulting in up to 31% improvement in AUROC to predict depression over the original imputation strategy. We conclude by discussing the challenges and opportunities with effective imputation in longitudinal sensing studies.

Wenda Xu, Jiachen Li, William Yang Wang et al.

Direct alignment from preferences (DAP) has emerged as a promising paradigm for aligning large language models (LLMs) to human desiderata from pre-collected, offline preference datasets. While recent studies indicate that existing offline DAP methods can directly benefit from online training samples, we highlight the need to develop specific online DAP algorithms to fully harness the power of online training. Specifically, we identify that the learned LLM should adhere to the proximity of the behavior LLM, which collects the training samples. To this end, we propose online Preference Optimization in proximity to the Behavior LLM (BPO), emphasizing the importance of constructing a proper trust region for LLM alignment. We conduct extensive experiments to validate the effectiveness and applicability of our approach by integrating it with various DAP methods, resulting in significant performance improvements across a wide range of tasks when training with the same amount of preference data. Even when only introducing one additional data collection phase, our online BPO improves its offline DAP baseline from 72.0% to 80.2% on TL;DR and from 82.2% to 89.1% on Anthropic Helpfulness in terms of win rate against human reference text.

Jiachen Li, Shuo Cheng, Zhenyu Liao et al.

Improving the sample efficiency of reinforcement learning algorithms requires effective exploration. Following the principle of $\textit{optimism in the face of uncertainty}$ (OFU), we train a separate exploration policy to maximize the approximate upper confidence bound of the critics in an off-policy actor-critic framework. However, this introduces extra differences between the replay buffer and the target policy regarding their stationary state-action distributions. To mitigate the off-policy-ness, we adapt the recently introduced DICE framework to learn a distribution correction ratio for off-policy RL training. In particular, we correct the training distribution for both policies and critics. Empirically, we evaluate our proposed method in several challenging continuous control tasks and show superior performance compared to state-of-the-art methods. We also conduct extensive ablation studies to demonstrate the effectiveness and rationality of the proposed method.

Akshay Dharmavaram, Tejus Gupta, Jiachen Li et al.

The current landscape of multi-agent expert imitation is broadly dominated by two families of algorithms - Behavioral Cloning (BC) and Adversarial Imitation Learning (AIL). BC approaches suffer from compounding errors, as they ignore the sequential decision-making nature of the trajectory generation problem. Furthermore, they cannot effectively model multi-modal behaviors. While AIL methods solve the issue of compounding errors and multi-modal policy training, they are plagued with instability in their training dynamics. In this work, we address this issue by introducing a novel self-supervised loss that encourages the discriminator to approximate a richer reward function. We employ our method to train a graph-based multi-agent actor-critic architecture that learns a centralized policy, conditioned on a learned latent interaction graph. We show that our method (SS-MAIL) outperforms prior state-of-the-art methods on real-world prediction tasks, as well as on custom-designed synthetic experiments. We prove that SS-MAIL is part of the family of AIL methods by providing a theoretical connection to cost-regularized apprenticeship learning. Moreover, we leverage the self-supervised formulation to introduce a novel teacher forcing-based curriculum (Trajectory Forcing) that improves sample efficiency by progressively increasing the length of the generated trajectory. The SS-MAIL framework improves multi-agent imitation capabilities by stabilizing the policy training, improving the reward shaping capabilities, as well as providing the ability for modeling multi-modal trajectories.

Jiachen Li, Quan Vuong, Shuang Liu et al.

We tackle the Multi-task Batch Reinforcement Learning problem. Given multiple datasets collected from different tasks, we train a multi-task policy to perform well in unseen tasks sampled from the same distribution. The task identities of the unseen tasks are not provided. To perform well, the policy must infer the task identity from collected transitions by modelling its dependency on states, actions and rewards. Because the different datasets may have state-action distributions with large divergence, the task inference module can learn to ignore the rewards and spuriously correlate $\textit{only}$ state-action pairs to the task identity, leading to poor test time performance. To robustify task inference, we propose a novel application of the triplet loss. To mine hard negative examples, we relabel the transitions from the training tasks by approximating their reward functions. When we allow further training on the unseen tasks, using the trained policy as an initialization leads to significantly faster convergence compared to randomly initialized policies (up to $80\%$ improvement and across 5 different Mujoco task distributions). We name our method $\textbf{MBML}$ ($\textbf{M}\text{ulti-task}$ $\textbf{B}\text{atch}$ RL with $\textbf{M}\text{etric}$ $\textbf{L}\text{earning}$).

Jiachen Li, Wei Zhan, Masayoshi Tomizuka

Accurate and robust tracking of surrounding road participants plays an important role in autonomous driving. However, there is usually no prior knowledge of the number of tracking targets due to object emergence, object disappearance and false alarms. To overcome this challenge, we propose a generic vehicle tracking framework based on modified mixture particle filter, which can make the number of tracking targets adaptive to real-time observations and track all the vehicles within sensor range simultaneously in a uniform architecture without explicit data association. Each object corresponds to a mixture component whose distribution is non-parametric and approximated by particle hypotheses. Most tracking approaches employ vehicle kinematic models as the prediction model. However, it is hard for these models to make proper predictions when sensor measurements are lost or become low quality due to partial or complete occlusions. Moreover, these models are incapable of forecasting sudden maneuvers. To address these problems, we propose to incorporate learning-based behavioral models instead of pure vehicle kinematic models to realize prediction in the prior update of recursive Bayesian state estimation. Two typical driving scenarios including lane keeping and lane change are demonstrated to verify the effectiveness and accuracy of the proposed framework as well as the advantages of employing learning-based models.