Back
PILCO: A Model-Based and Data-Efficient Approach to Policy Search
In this paper, we introduce PILCO, a practical, data-efficient model-based policy search method. PILCO reduces model bias, one of the key problems of model-based reinforcement learning, in a principled way. By learning a probabilistic dynamics model and explicitly incorporating model uncertainty into long-term planning, PILCO can cope with very little data and facilitates learning from scratch in only a few trials. Policy evaluation is performed in closed form using state-of-the-art approximate inference. Furthermore, policy gradients are computed analytically for policy improvement. We report unprecedented learning efficiency on challenging and high-dimensional control tasks.
@inproceedings{DeisenrothRT2011, title = {PILCO: A Model-Based and Data-Efficient Approach to Policy Search}, booktitle = {Proceedings of the 28th International Conference on Machine Learning, ICML 2011}, abstract = {In this paper, we introduce PILCO, a practical, data-efficient model-based policy search method. PILCO reduces model bias, one of the key problems of model-based reinforcement learning, in a principled way. By learning a probabilistic dynamics model and explicitly incorporating model uncertainty into long-term planning, PILCO can cope with very little data and facilitates learning from scratch in only a few trials. Policy evaluation is performed in closed form using state-of-the-art approximate inference. Furthermore, policy gradients are computed analytically for policy improvement. We report unprecedented learning efficiency on challenging and high-dimensional control tasks. }, pages = {465-472}, editors = {L Getoor and T Scheffer}, publisher = {Omnipress}, year = {2011}, slug = {deisenrothrt2011}, author = {Deisenroth, MP. and Rasmussen, CE.} }