@inproceedings{8377f97d8c0a410c8284bff72e06aeb1,
title = "Action Elimination and Stopping Conditions for Reinforcement Learning",
abstract = "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.",
author = "Eyal Even-Dar and Shie Mannor and Yishay Mansour",
year = "2003",
language = "אנגלית",
isbn = "1577351894",
series = "Proceedings, Twentieth International Conference on Machine Learning",
pages = "162--169",
editor = "T. Fawcett and N. Mishra",
booktitle = "Proceedings, Twentieth International Conference on Machine Learning",
note = "Proceedings, Twentieth International Conference on Machine Learning ; Conference date: 21-08-2003 Through 24-08-2003",
}