Action Elimination and Stopping Conditions for Reinforcement Learning

Eyal Even-Dar, Shie Mannor, and Yishay Mansour

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.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.