I am a MS student at Fudan University, advised by Prof. Wei Li.
Research interest
I am broadly interested in research on Reinforcement Learning, and my current research interest primarily focuses on:
- Generalization & Adaptation (Cross-Dynamics/Rewards/Embodiment; Meta RL; Robustness; Pre-training)
- Learning with Prior Knowledge (LfD; Offline-Online; Policy/Primitive/Skill Reuse)
- Human-in-the-Loop (Task Specification with Preferences / Symbolic Representation / Language Instruction)
Publications and preprints
Cross-Domain Policy Adaptation via Value-Guided Data Filtering
Kang Xu, Chenjia Bai, Xiaoteng Ma, Dong Wang, Bin Zhao, Zhen Wang, Xuelong Li, Wei Li
Neural Information Processing Systems (NeurIPS), 2023
[Paper] [Code]
Kang Xu, Chenjia Bai, Xiaoteng Ma, Dong Wang, Bin Zhao, Zhen Wang, Xuelong Li, Wei Li
Neural Information Processing Systems (NeurIPS), 2023
[Paper] [Code]
Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning
Haoran He, Chenjia Bai, Kang Xu, Zhuoran Yang, Weinan Zhang, Zhen Wang, Bin Zhao, Xuelong Li
Neural Information Processing Systems (NeurIPS), 2023
[Paper] [Code]
Haoran He, Chenjia Bai, Kang Xu, Zhuoran Yang, Weinan Zhang, Zhen Wang, Bin Zhao, Xuelong Li
Neural Information Processing Systems (NeurIPS), 2023
[Paper] [Code]
On the Value of Myopic Behavior in Policy Reuse
Kang Xu, Chenjia Bai, Shuang Qiu, Haoran He, Bin Zhao, Zhen Wang, Wei Li, Xuelong Li
Preprint 2023
[Paper]
Kang Xu, Chenjia Bai, Shuang Qiu, Haoran He, Bin Zhao, Zhen Wang, Wei Li, Xuelong Li
Preprint 2023
[Paper]
Open-Ended Diverse Solution Discovery with Regulated Behavior Patterns for Cross-Domain Adaptation
Kang Xu, Yan Ma, Bingsheng Wei, Wei Li
Association for the Advancement of Artificial Intelligence (AAAI), 2023 (Oral)
[Paper]
Kang Xu, Yan Ma, Bingsheng Wei, Wei Li
Association for the Advancement of Artificial Intelligence (AAAI), 2023 (Oral)
[Paper]
Quantification before Selection: Active Dynamics Preference for Robust Reinforcement Learning
Kang Xu, Yan Ma, Wei Li
Preprint 2022
[Paper]
Kang Xu, Yan Ma, Wei Li
Preprint 2022
[Paper]
Dynamics-aware novelty search with behavior repulsion
Kang Xu, Yan Ma, Wei Li
Genetic and Evolutionary Computation Conference (GECCO), 2022
[Paper]
Kang Xu, Yan Ma, Wei Li
Genetic and Evolutionary Computation Conference (GECCO), 2022
[Paper]
Evolutionary Action Selection for Gradient-Based Policy Learning
Yan Ma, Tianxing Liu, Bingsheng Wei, Yi Liu, Kang Xu, Wei Li
International Conference on Neural Information Processing (ICONIP), 2022 (Oral)
[Paper]
Yan Ma, Tianxing Liu, Bingsheng Wei, Yi Liu, Kang Xu, Wei Li
International Conference on Neural Information Processing (ICONIP), 2022 (Oral)
[Paper]
Experiences
Netease Fuxi - Algorithm Engineer Intern (Jun.2021 - Aug.2021)