Examining Policy Entropy of Reinforcement Learning Agents for Personalization Tasks
This addresses the problem of policy entropy differences in RL for personalization, which is incremental as it compares existing methods.
The paper examines how reinforcement learning agents behave in personalization tasks, finding that Policy Optimization agents develop low-entropy policies that prioritize certain actions, while Q-Learning agents maintain high-entropy policies, which is often better for real-world use.
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, which is often preferable in real-world applications. We provide a wide range of numerical experiments as well as theoretical justification to show that these differences in entropy are due to the type of learning being employed.