Showing 2025Show all
2 papers · 1 filter
cs.LG2025
Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL
Guojian Zhan, Likun Wang, Pengcheng Wang +4
Maximum entropy has become a mainstream off-policy reinforcement learning (RL) framework for balancing exploitation and exploration. However, two bottlenecks still limit further pe…
cs.LG2025
Residual Policy Gradient: A Reward View of KL-regularized Objective
Pengcheng Wang, Xinghao Zhu, Yuxin Chen +3
Reinforcement Learning and Imitation Learning have achieved widespread success in many domains but remain constrained during real-world deployment. One of the main issues is the ad…