3 papers
cs.LG2025
When Maximum Entropy Misleads Policy Optimization
Ruipeng Zhang, Ya-Chien Chang, Sicun Gao
The Maximum Entropy Reinforcement Learning (MaxEnt RL) framework is a leading approach for achieving efficient learning and robust performance across many RL tasks. However, MaxEnt…
cs.LG2024
Extremum-Seeking Action Selection for Accelerating Policy Optimization
Ya-Chien Chang, Sicun Gao
Reinforcement learning for control over continuous spaces typically uses high-entropy stochastic policies, such as Gaussian distributions, for local exploration and estimating poli…
cs.RO2023
Learning Stabilization Control from Observations by Learning Lyapunov-like Proxy Models
Milan Ganai, Chiaki Hirayama, Ya-Chien Chang +1
The deployment of Reinforcement Learning to robotics applications faces the difficulty of reward engineering. Therefore, approaches have focused on creating reward functions by Lea…