Dexterous Hand Manipulation via Efficient Imitation-Bootstrapped Online Reinforcement Learning

Dexterous hand manipulation in real-world scenarios presents considerable challenges due to its demands for both dexterity and precision. While imitation learning approaches have thoroughly examined these challenges, they still require a significant number of expert demonstrations and are limited by a constrained performance upper bound. In this paper, we propose a novel and efficient Imitation-Bootstrapped Online Reinforcement Learning (IBORL) method tailored for robotic dexterous hand manipulation in real-world environments. Specifically, we pretrain the policy using a limited set of expert demonstrations and subsequently finetune this policy through direct reinforcement learning in the real world. To address the catastrophic forgetting issues that arise from the distribution shift between expert demonstrations and real-world environments, we design a regularization term that balances the exploration of novel behaviors with the preservation of the pretrained policy. Our experiments with real-world tasks demonstrate that our method significantly outperforms existing approaches, achieving an almost 100% success rate and a 23% improvement in cycle time. Furthermore, by finetuning with online reinforcement learning, our method surpasses expert demonstrations and uncovers superior policies. Our code and empirical results are available in https://hggforget.github.io/iborl.github.io/.

Egocentric Vision Language Planning

We explore leveraging large multi-modal models (LMMs) and text2image models to build a more general embodied agent. LMMs excel in planning long-horizon tasks over symbolic abstractions but struggle with grounding in the physical world, often failing to accurately identify object positions in images. A bridge is needed to connect LMMs to the physical world. The paper proposes a novel approach, egocentric vision language planning (EgoPlan), to handle long-horizon tasks from an egocentric perspective in varying household scenarios. This model leverages a diffusion model to simulate the fundamental dynamics between states and actions, integrating techniques like style transfer and optical flow to enhance generalization across different environmental dynamics. The LMM serves as a planner, breaking down instructions into sub-goals and selecting actions based on their alignment with these sub-goals, thus enabling more generalized and effective decision-making. Experiments show that EgoPlan improves long-horizon task success rates from the egocentric view compared to baselines across household scenarios.