Performance Bounds for Lambda Policy Iteration and Application to the Game of Tetris

Bruno Scherrer 1
1 MAIA - Autonomous intelligent machine
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : We consider the discrete-time infinite-horizon optimal control problem formalized by Markov Decision Processes. We revisit the work of Bertsekas and Ioffe, that introduced $\lambda$ Policy Iteration, a family of algorithms parameterized by $\lambda$ that generalizes the standard algorithms Value Iteration and Policy Iteration, and has some deep connections with the Temporal Differences algorithm TD($\lambda$) described by Sutton and Barto. We deepen the original theory developped by the authors by providing convergence rate bounds which generalize standard bounds for Value Iteration described for instance by Puterman. Then, the main contribution of this paper is to develop the theory of this algorithm when it is used in an approximate form and show that this is sound. Doing so, we extend and unify the separate analyses developped by Munos for Approximate Value Iteration and Approximate Policy Iteration. Eventually, we revisit the use of this algorithm in the training of a Tetris playing controller as originally done by Bertsekas and Ioffe. We provide an original performance bound that can be applied to such an undiscounted control problem. Our empirical results are different from those of Bertsekas and Ioffe (which were originally qualified as ''paradoxical'' and ''intriguing''), and much more conform to what one would expect from a learning experiment. We discuss the possible reason for such a difference.
Type de document :
Rapport
[Research Report] RR-6348, 2011, pp.54
Liste complète des métadonnées

https://hal.inria.fr/inria-00185271
Contributeur : Bruno Scherrer <>
Soumis le : mardi 11 octobre 2011 - 14:15:52
Dernière modification le : jeudi 11 janvier 2018 - 06:19:51
Document(s) archivé(s) le : jeudi 12 janvier 2012 - 02:30:58

Fichiers

article.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00185271, version 5
  • ARXIV : 0711.0694

Collections

Citation

Bruno Scherrer. Performance Bounds for Lambda Policy Iteration and Application to the Game of Tetris. [Research Report] RR-6348, 2011, pp.54. 〈inria-00185271v5〉

Partager

Métriques

Consultations de la notice

366

Téléchargements de fichiers

135