36 citations · 91 across the 20 of their papers we have counts for
8 papers · 1 filter
Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations
Renzhe Zhou, Chen-Xiao Gao, Zongzhang Zhang +1
Generalization and sample efficiency have been long-standing issues concerning reinforcement learning, and thus the field of Offline Meta-Reinforcement Learning~(OMRL) has gained i…
Imitator Learning: Achieve Out-of-the-Box Imitation Ability in Variable Environments
Xiong-Hui Chen, Junyin Ye, Hang Zhao +9
Imitation learning (IL) enables agents to mimic expert behaviors. Most previous IL techniques focus on precisely imitating one policy through mass demonstrations. However, in many…
ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning
Chen-Xiao Gao, Chenyang Wu, Mingjun Cao +3
Decision Transformer (DT), which employs expressive sequence modeling techniques to perform action generation, has emerged as a promising approach to offline policy optimization. H…
Policy Regularization with Dataset Constraint for Offline Reinforcement Learning
Yuhang Ran, Yi-Chen Li, Fuxiang Zhang +2
We consider the problem of learning the best possible policy from a fixed dataset, known as offline Reinforcement Learning (RL). A common taxonomy of existing offline RL works is p…
Language Model Self-improvement by Reinforcement Learning Contemplation
Jing-Cheng Pang, Pengyuan Wang, Kaiyuan Li +4
Large Language Models (LLMs) have exhibited remarkable performance across various natural language processing (NLP) tasks. However, fine-tuning these models often necessitates subs…
How To Guide Your Learner: Imitation Learning with Active Adaptive Expert Involvement
Xu-Hui Liu, Feng Xu, Xinyu Zhang +5
Imitation learning aims to mimic the behavior of experts without explicit reward signals. Passive imitation learning methods which use static expert datasets typically suffer from…
Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learning
Cong Guan, Feng Chen, Lei Yuan +2
Utilizing messages from teammates can improve coordination in cooperative Multi-agent Reinforcement Learning (MARL). Previous works typically combine raw messages of teammates with…
Retrosynthetic Planning with Dual Value Networks
Guoqing Liu, Di Xue, Shufang Xie +7
Retrosynthesis, which aims to find a route to synthesize a target molecule from commercially available starting materials, is a critical task in drug discovery and materials design…