Examining Policy Entropy of Reinforcement Learning Agents for Personalization Tasks

arXiv:2211.11869v4 Announce Type: replace
Abstract: This effort is focused on examining the behavior of reinforcement learning systems in personalization environments and detailing the differences in policy entropy associated with the type of learning algorithm utilized. We demonstrate that Policy Optimization agents often possess low-entropy policies during training, which in practice results in agents prioritizing certain actions and avoiding others. Conversely, we also show that Q-Learning agents are far less susceptible to such behavior and generally maintain high-entropy policies throughout training, …

abstract agents algorithm arxiv behavior cs.ai cs.lg cs.na differences entropy environments learning systems low math.na math.oc optimization personalization policies policy practice reinforcement reinforcement learning systems tasks training type