Actor-Critic Reinforcement Learning with Phased Actor

arXiv:2404.11834v1 Announce Type: new
Abstract: Policy gradient methods in actor-critic reinforcement learning (RL) have become perhaps the most promising approaches to solving continuous optimal control problems. However, the trial-and-error nature of RL and the inherent randomness associated with solution approximations cause variations in the learned optimal values and policies. This has significantly hindered their successful deployment in real life applications where control responses need to meet dynamic performance criteria deterministically. Here we propose a novel phased actor in actor-critic (PAAC) …

abstract actor actor-critic arxiv become continuous control cs.lg error gradient however nature policies policy randomness reinforcement reinforcement learning solution type values