2 papers
cs.LG2023
Beyond Reward: Offline Preference-guided Policy Optimization
Yachen Kang, Diyuan Shi, Jinxin Liu +2
This study focuses on the topic of offline preference-based reinforcement learning (PbRL), a variant of conventional reinforcement learning that dispenses with the need for online…
cs.LG2021
Off-Dynamics Inverse Reinforcement Learning from Hetero-Domain
Yachen Kang, Jinxin Liu, Xin Cao +1
We propose an approach for inverse reinforcement learning from hetero-domain which learns a reward function in the simulator, drawing on the demonstrations from the real world. The…