← Search

Mingjun Cao

2 accepted papers

2025

Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning

ICML 2025poster

Behavior regularization, which constrains the policy to stay close to some behavior policy, is widely used in offline reinforcement learning (RL) to manage the risk of hazardous exploitation of unseen actions. Nevertheless, existing literature on behavior-regularized RL primarily focuses on explicit…

Cited by 1SourcePDFScholar
2024

ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning

AAAI 2024technical

Decision Transformer (DT), which employs expressive sequence modeling techniques to perform action generation, has emerged as a promising approach to offline policy optimization. However, DT generates actions conditioned on a desired future return, which is known to bear some weaknesses such as the…