Back
Reward-Weighted Regression with Sample Reuse for Direct Policy Search in Reinforcement Learning
Direct policy search is a promising reinforcement learning framework, in particular for controlling continuous, high-dimensional systems. Policy search often requires a large number of samples for obtaining a stable policy update estimator, and this is prohibitive when the sampling cost is expensive. In this letter, we extend an expectation-maximization-based policy search method so that previously collected samples can be efficiently reused. The usefulness of the proposed method, reward-weighted regression with sample reuse (R), is demonstrated through robot learning experiments.
@article{HachiyaPS2011, title = {Reward-Weighted Regression with Sample Reuse for Direct Policy Search in Reinforcement Learning}, journal = {Neural Computation}, abstract = {Direct policy search is a promising reinforcement learning framework, in particular for controlling continuous, high-dimensional systems. Policy search often requires a large number of samples for obtaining a stable policy update estimator, and this is prohibitive when the sampling cost is expensive. In this letter, we extend an expectation-maximization-based policy search method so that previously collected samples can be efficiently reused. The usefulness of the proposed method, reward-weighted regression with sample reuse (R), is demonstrated through robot learning experiments. }, volume = {23}, number = {11}, pages = {2798-2832}, month = nov, year = {2011}, slug = {hachiyaps2011}, author = {Hachiya, H. and Peters, J. and Sugiyama, M.}, month_numeric = {11} }