The many faces of optimism - Extended version

Autor:	Szita, István, Lőrincz, András
Rok vydání:	2008
Předmět:	Computer Science - Artificial Intelligence Computer Science - Computational Complexity Computer Science - Learning
Druh dokumentu:	Working Paper
Popis:	The exploration-exploitation dilemma has been an intriguing and unsolved problem within the framework of reinforcement learning. "Optimism in the face of uncertainty" and model building play central roles in advanced exploration methods. Here, we integrate several concepts and obtain a fast and simple algorithm. We show that the proposed algorithm finds a near-optimal policy in polynomial time, and give experimental evidence that it is robust and efficient compared to its ascendants. Comment: Extended version of the homonymous ICML'08 paper, with proofs
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/0810.3451 Zobrazit plný text záznamu View this record from Arxiv