λ方策反復の性能限界とテトリスへの応用
Performance Bounds for Lambda Policy Iteration and Application to the Game of Tetris
λ方策反復の収束率限界を導出し、近似版の理論を整備した上で、テトリス制御器の学習に適用して従来の「逆説的」な結果を再検討した論文。
著者: Bruno Scherrer
分類: cs.AI, cs.RO
原文アブストラクト
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.
