Xiao Ma

Xiao Ma, Bingyi Kang, Zhongwen Xu et al.

The major challenge of offline RL is the distribution shift that appears when out-of-distribution actions are queried, which makes the policy improvement direction biased by extrapolation errors. Most existing methods address this problem by penalizing the policy or value for deviating from the behavior policy during policy improvement or evaluation. In this work, we propose a novel MISA framework to approach offline RL from the perspective of Mutual Information between States and Actions in the dataset by directly constraining the policy improvement direction. MISA constructs lower bounds of mutual information parameterized by the policy and Q-values. We show that optimizing this lower bound is equivalent to maximizing the likelihood of a one-step improved policy on the offline dataset. Hence, we constrain the policy improvement direction to lie in the data manifold. The resulting algorithm simultaneously augments the policy evaluation and improvement by adding mutual information regularizations. MISA is a general framework that unifies conservative Q-learning (CQL) and behavior regularization methods (e.g., TD3+BC) as special cases. We introduce 3 different variants of MISA, and empirically demonstrate that tighter mutual information lower bound gives better offline RL performance. In addition, our extensive experiments show MISA significantly outperforms a wide range of baselines on various tasks of the D4RL benchmark,e.g., achieving 742.9 total points on gym-locomotion tasks. Our code is available at https://github.com/sail-sg/MISA.

Jiawei Ren, Cunjun Yu, Siwei Chen et al.

Motion mimicking is a foundational task in physics-based character animation. However, most existing motion mimicking methods are built upon reinforcement learning (RL) and suffer from heavy reward engineering, high variance, and slow convergence with hard explorations. Specifically, they usually take tens of hours or even days of training to mimic a simple motion sequence, resulting in poor scalability. In this work, we leverage differentiable physics simulators (DPS) and propose an efficient motion mimicking method dubbed DiffMimic. Our key insight is that DPS casts a complex policy learning task to a much simpler state matching problem. In particular, DPS learns a stable policy by analytical gradients with ground-truth physical priors hence leading to significantly faster and stabler convergence than RL-based methods. Moreover, to escape from local optima, we utilize a Demonstration Replay mechanism to enable stable gradient backpropagation in a long horizon. Extensive experiments on standard benchmarks show that DiffMimic has a better sample efficiency and time efficiency than existing methods (e.g., DeepMimic). Notably, DiffMimic allows a physically simulated character to learn Backflip after 10 minutes of training and be able to cycle it after 3 hours of training, while the existing approach may require about a day of training to cycle Backflip. More importantly, we hope DiffMimic can benefit more differentiable animation systems with techniques like differentiable clothes simulation in future research.

Bingyi Kang, Xiao Ma, Chao Du et al.

Offline reinforcement learning (RL) aims to learn optimal policies from offline datasets, where the parameterization of policies is crucial but often overlooked. Recently, Diffsuion-QL significantly boosts the performance of offline RL by representing a policy with a diffusion model, whose success relies on a parametrized Markov Chain with hundreds of steps for sampling. However, Diffusion-QL suffers from two critical limitations. 1) It is computationally inefficient to forward and backward through the whole Markov chain during training. 2) It is incompatible with maximum likelihood-based RL algorithms (e.g., policy gradient methods) as the likelihood of diffusion models is intractable. Therefore, we propose efficient diffusion policy (EDP) to overcome these two challenges. EDP approximately constructs actions from corrupted ones at training to avoid running the sampling chain. We conduct extensive experiments on the D4RL benchmark. The results show that EDP can reduce the diffusion policy training time from 5 days to 5 hours on gym-locomotion tasks. Moreover, we show that EDP is compatible with various offline RL algorithms (TD3, CRR, and IQL) and achieves new state-of-the-art on D4RL by large margins over previous methods. Our code is available at https://github.com/sail-sg/edp.

Peiyan Li, Yixiang Chen, Hongtao Wu et al.

Recently, leveraging pre-trained vision-language models (VLMs) for building vision-language-action (VLA) models has emerged as a promising approach to effective robot manipulation learning. However, only few methods incorporate 3D signals into VLMs for action prediction, and they do not fully leverage the spatial structure inherent in 3D data, leading to low sample efficiency. In this paper, we introduce BridgeVLA, a novel 3D VLA model that (1) projects 3D inputs to multiple 2D images, ensuring input alignment with the VLM backbone, and (2) utilizes 2D heatmaps for action prediction, unifying the input and output spaces within a consistent 2D image space. In addition, we propose a scalable pre-training method that equips the VLM backbone with the capability to predict 2D heatmaps before downstream policy learning. Extensive experiments show the proposed method is able to learn 3D manipulation efficiently and effectively. BridgeVLA outperforms state-of-the-art baseline methods across three simulation benchmarks. In RLBench, it improves the average success rate from 81.4% to 88.2%. In COLOSSEUM, it demonstrates significantly better performance in challenging generalization settings, boosting the average success rate from 56.7% to 64.0%. In GemBench, it surpasses all the comparing baseline methods in terms of average success rate. In real-robot experiments, BridgeVLA outperforms a state-of-the-art baseline method by 32% on average. It generalizes robustly in multiple out-of-distribution settings, including visual disturbances and unseen instructions. Remarkably, it is able to achieve a success rate of 96.8% on 10+ tasks with only 3 trajectories per task, highlighting its extraordinary sample efficiency. Project Website:https://bridgevla.github.io/

Qingyuan Jiang, Zhouyang Chi, Xiao Ma et al.

To address the modality learning degeneration caused by modality imbalance, existing multimodal learning~(MML) approaches primarily attempt to balance the optimization process of each modality from the perspective of model learning. However, almost all existing methods ignore the modality imbalance caused by unimodal data sampling, i.e., equal unimodal data sampling often results in discrepancies in informational content, leading to modality imbalance. Therefore, in this paper, we propose a novel MML approach called \underline{D}ata-aware \underline{U}nimodal \underline{S}ampling~(\method), which aims to dynamically alleviate the modality imbalance caused by sampling. Specifically, we first propose a novel cumulative modality discrepancy to monitor the multimodal learning process. Based on the learning status, we propose a heuristic and a reinforcement learning~(RL)-based data-aware unimodal sampling approaches to adaptively determine the quantity of sampled data at each iteration, thus alleviating the modality imbalance from the perspective of sampling. Meanwhile, our method can be seamlessly incorporated into almost all existing multimodal learning approaches as a plugin. Experiments demonstrate that \method~can achieve the best performance by comparing with diverse state-of-the-art~(SOTA) baselines.