Performance Bounds for Lambda Policy Iteration and Application to the Game of Tetris - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Journal of Machine Learning Research Year : 2013

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

Bruno Scherrer

Abstract

We consider the discrete-time infinite-horizon optimal control problem formalized by Markov decision processes (Puterman, 1994; Bertsekas and Tsitsiklis, 1996). We revisit the work of Bertsekas and Ioffe (1996), that introduced $\lambda$ policy iteration-a family of algorithms parametrized by a parameter $\lambda$-that generalizes the standard algorithms value and policy iteration, and has some deep connections with the temporal-difference algorithms described by Sutton and Barto (1998). We deepen the original theory developed by the authors by providing convergence rate bounds which generalize standard bounds for value iteration described for instance by Puterman (1994). Then, the main contribution of this paper is to develop the theory of this algorithm when it is used in an approximate form. We extend and unify the separate analyzes developed by Munos for approximate value iteration (Munos, 2003) and approximate policy iteration (Munos, 2003), and provide performance bounds in the discounted and the undiscounted situations. Finally, we revisit the use of this algorithm in the training of a Tetris playing controller as originally done by Bertsekas and Ioffe (1996).. Our empirical results are different from those of Bertsekas and Ioffe (which were originally qualified as "paradoxical" and "intriguing"). We track down the reason to be a minor implementation error of the algorithm, which suggests that, in practice, $\lambda$ policy iteration may be more stable than previously thought.
Fichier principal
Vignette du fichier
article.pdf (429.93 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00759102 , version 1 (30-11-2012)
hal-00759102 , version 2 (26-04-2013)

Identifiers

Cite

Bruno Scherrer. Performance Bounds for Lambda Policy Iteration and Application to the Game of Tetris. Journal of Machine Learning Research, 2013, 14, pp.1175-1221. ⟨hal-00759102v2⟩
289 View
545 Download

Altmetric

Share

Gmail Facebook X LinkedIn More