Regularized Conditional Diffusion Model for Multi-Task Preference Alignment

no code implementations • 7 Apr 2024 • Xudong Yu, Chenjia Bai, Haoran He, Changhong Wang, Xuelong Li

Sequential decision-making is desired to align with human intents and exhibit versatility across various tasks.

D4RL Decision Making

Large-Scale Actionless Video Pre-Training via Discrete Diffusion for Efficient Policy Learning

no code implementations • 22 Feb 2024 • Haoran He, Chenjia Bai, Ling Pan, Weinan Zhang, Bin Zhao, Xuelong Li

In the fine-tuning stage, we harness the imagined future videos to guide low-level action learning trained on a limited set of robot data.

Diffusion Models for Reinforcement Learning: A Survey

1 code implementation • 2 Nov 2023 • Zhengbang Zhu, Hanye Zhao, Haoran He, Yichao Zhong, Shenyu Zhang, Haoquan Guo, Tingting Chen, Weinan Zhang

Diffusion models surpass previous generative models in sample quality and training stability.

reinforcement-learning Reinforcement Learning (RL)

Privileged Knowledge Distillation for Sim-to-Real Policy Generalization

1 code implementation • 29 May 2023 • Haoran He, Chenjia Bai, Hang Lai, Lingxiao Wang, Weinan Zhang

In this paper, we propose a novel single-stage privileged knowledge distillation method called the Historical Information Bottleneck (HIB) to narrow the sim-to-real gap.

Knowledge Distillation Reinforcement Learning (RL)

Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning

1 code implementation • NeurIPS 2023 • Haoran He, Chenjia Bai, Kang Xu, Zhuoran Yang, Weinan Zhang, Dong Wang, Bin Zhao, Xuelong Li

Specifically, we propose Multi-Task Diffusion Model (\textsc{MTDiff}), a diffusion-based method that incorporates Transformer backbones and prompt learning for generative planning and data synthesis in multi-task offline settings.

Reinforcement Learning (RL)

On the Value of Myopic Behavior in Policy Reuse

no code implementations • 28 May 2023 • Kang Xu, Chenjia Bai, Shuang Qiu, Haoran He, Bin Zhao, Zhen Wang, Wei Li, Xuelong Li

Leveraging learned strategies in unfamiliar scenarios is fundamental to human intelligence.