Publication
Relative Entropy Policy Search
Jan Peters; Katharina Mülling; Yasemin Altun
In: Maria Fox; David Poole (Hrsg.). Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence (AAAI-2010), July 11-15, Atlanta, Georgia, USA, AAAI Press, 2010.
Abstract
Policy search is a successful approach to reinforcement learning. However, policy improvements often result in the loss of information. Hence, it has been marred by premature convergence and implausible solutions. As first suggested in the context of covariant policy gradients, many of these problems may be addressed by constraining the information loss. In this paper, we continue this path of reasoning and suggest the Relative Entropy Policy Search (REPS) method. The resulting method differs significantly from previous policy gradient approaches and yields an exact update step. It can be shown to work well on typical reinforcement learning benchmark problems.