Learning Optimal Deterministic Policies with Stochastic Policy Gradients

arXiv:2405.02235v1 Announce Type: new
Abstract: Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. They learn stochastic parametric (hyper)policies by either exploring in the space of actions or in the space of parameters. Stochastic controllers, however, are often undesirable from a practical perspective because of their lack of robustness, safety, and traceability. In common practice, stochastic (hyper)policies are learned only to deploy their deterministic version. In this paper, we make a step towards the …

abstract arxiv continuous cs.lg deal gradient however learn parameters parametric perspective policies policy practical reinforcement reinforcement learning space stochastic type