Action Elimination and Stopping Conditions for Reinforcement Learning

We consider incorporating action elimination procedures in reinforcement learning algorithms. We suggest a framework that is based on learning an upper and a lower estimates of the value function or the Q-function and eliminating actions that are not optimal. We provide a model-based and a model-free variants of the elimination method. We further derive stopping conditions that guarantee that the learned policy is approximately optimal with high probability. Simulations demonstrate a considerable speedup and added robustness.

• Type: Conference
• Year: 2003
• Where: ICML
• Authors: Eyal Even-Dar, Shie Mannor, Yishay Mansour
• Keywords: Action Elimination Procedures, Elimination Method, ICML 2003, Machine Learning, Reinforcement Learning Algorithms