Zobrazeno 1 - 10
of 83
pro vyhledávání: '"Bai, Chenjia"'
Autor:
Lyu, Jiafei, Xu, Kang, Xu, Jiacheng, Yan, Mengbei, Yang, Jingwen, Zhang, Zongzhang, Bai, Chenjia, Lu, Zongqing, Li, Xiu
We consider off-dynamics reinforcement learning (RL) where one needs to transfer policies across different domains with dynamics mismatch. Despite the focus on developing dynamics-aware algorithms, this field is hindered due to the lack of a standard
Externí odkaz:
http://arxiv.org/abs/2410.20750
Autor:
Yuan, Xinyi, Shang, Zhiwei, Wang, Zifan, Wang, Chenkai, Shan, Zhao, Qi, Zhenchao, Zhu, Meixin, Bai, Chenjia, Li, Xuelong
Diffusion models demonstrate superior performance in capturing complex distributions from large-scale datasets, providing a promising solution for quadrupedal locomotion control. However, offline policy is sensitive to Out-of-Distribution (OOD) state
Externí odkaz:
http://arxiv.org/abs/2410.13586
Diffusion models have demonstrated their capabilities in modeling trajectories of multi-tasks. However, existing multi-task planners or policies typically rely on task-specific demonstrations via multi-task imitation, or require task-specific reward
Externí odkaz:
http://arxiv.org/abs/2409.19949
Diffusion models have achieved remarkable success in sequential decision-making by leveraging the highly expressive model capabilities in policy learning. A central problem for learning diffusion policies is to align the policy output with human inte
Externí odkaz:
http://arxiv.org/abs/2409.05622
Policy constraint methods in offline reinforcement learning employ additional regularization techniques to constrain the discrepancy between the learned policy and the offline dataset. However, these methods tend to result in overly conservative poli
Externí odkaz:
http://arxiv.org/abs/2408.02165
Learning a world model for model-free Reinforcement Learning (RL) agents can significantly improve the sample efficiency by learning policies in imagination. However, building a world model for Multi-Agent RL (MARL) can be particularly challenging du
Externí odkaz:
http://arxiv.org/abs/2406.15836
Autor:
Zhang, Junjie, Bai, Chenjia, He, Haoran, Xia, Wenke, Wang, Zhigang, Zhao, Bin, Li, Xiu, Li, Xuelong
Acquiring a multi-task imitation policy in 3D manipulation poses challenges in terms of scene understanding and action prediction. Current methods employ both 3D representation and multi-view 2D representation to predict the poses of the robot's end-
Externí odkaz:
http://arxiv.org/abs/2405.19586
Unsupervised Reinforcement Learning (RL) provides a promising paradigm for learning useful behaviors via reward-free per-training. Existing methods for unsupervised RL mainly conduct empowerment-driven skill discovery or entropy-based exploration. Ho
Externí odkaz:
http://arxiv.org/abs/2405.16030
It is vital to learn effective policies that can be transferred to different domains with dynamics discrepancies in reinforcement learning (RL). In this paper, we consider dynamics adaptation settings where there exists dynamics mismatch between the
Externí odkaz:
http://arxiv.org/abs/2405.15369
Grounding the reasoning ability of large language models (LLMs) for embodied tasks is challenging due to the complexity of the physical world. Especially, LLM planning for multi-agent collaboration requires communication of agents or credit assignmen
Externí odkaz:
http://arxiv.org/abs/2405.14314