Optimistic Initialization and Greediness Lead to Polynomial Time Learning in Factored MDPs - Extended Version

Autor:	Szita, Istvan, Lorincz, Andras
Rok vydání:	2009
Předmět:	Computer Science - Artificial Intelligence Computer Science - Learning
Druh dokumentu:	Working Paper
Popis:	In this paper we propose an algorithm for polynomial-time reinforcement learning in factored Markov decision processes (FMDPs). The factored optimistic initial model (FOIM) algorithm, maintains an empirical model of the FMDP in a conventional way, and always follows a greedy policy with respect to its model. The only trick of the algorithm is that the model is initialized optimistically. We prove that with suitable initialization (i) FOIM converges to the fixed point of approximate value iteration (AVI); (ii) the number of steps when the agent makes non-near-optimal decisions (with respect to the solution of AVI) is polynomial in all relevant quantities; (iii) the per-step costs of the algorithm are also polynomial. To our best knowledge, FOIM is the first algorithm with these properties. This extended version contains the rigorous proofs of the main theorem. A version of this paper appeared in ICML'09. Comment: This paper is the extended version of a similarly named paper appearing in ICML'09, containing the rigorous proofs of the main theorem
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/0904.3352 Zobrazit plný text záznamu View this record from Arxiv