Relative Entropy Policy Search

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 (Bagnell and Schneider 2003), 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 works well on typical reinforcement learning benchmark problems.

[1]  Christopher G. Atkeson,et al.  Using Local Trajectory Optimizers to Speed Up Global Optimization in Dynamic Programming , 1993, NIPS.

[2]  Martin L. Puterman,et al.  Markov Decision Processes: Discrete Stochastic Dynamic Programming , 1994 .

[3]  Andrew G. Barto,et al.  Reinforcement learning , 1998 .

[4]  Richard S. Sutton,et al.  Introduction to Reinforcement Learning , 1998 .

[5]  Richard S. Sutton,et al.  Dimensions of Reinforcement Learning , 1998 .

[6]  Yishay Mansour,et al.  Policy Gradient Methods for Reinforcement Learning with Function Approximation , 1999, NIPS.

[7]  Sham M. Kakade,et al.  A Natural Policy Gradient , 2001, NIPS.

[8]  Leonid Peshkin,et al.  Learning from Scarce Experience , 2002, ICML.

[9]  Jeff G. Schneider,et al.  Covariant policy search , 2003, IJCAI 2003.

[10]  Benjamin Van Roy,et al.  The Linear Programming Approach to Approximate Dynamic Programming , 2003, Oper. Res..

[11]  Shie Mannor,et al.  Biases and Variance in Value Function Estimates , 2004 .

[12]  Stefan Schaal,et al.  Natural Actor-Critic , 2003, Neurocomputing.

[13]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[14]  Sugiyama Masashi,et al.  Adaptive Importance Sampling with Automatic Model Selection in Value Function Approximation , 2007 .

[15]  Jan Peters,et al.  Policy Search for Motor Primitives in Robotics , 2008, NIPS 2008.

[16]  David Barber,et al.  Variational methods for Reinforcement Learning , 2010, AISTATS.

[17]  Marc Peter Deisenroth,et al.  Efficient reinforcement learning using Gaussian processes , 2010 .