Publisher = {JMLR Workshop and Conference Proceedings},

Title = {Sample Efficient Reinforcement Learning with Gaussian Processes},

Url = {http://jmlr.org/proceedings/papers/v32/grande14.pdf},

Abstract = {This paper derives sample complexity results for using Gaussian Processes (GPs) in both model-based and model-free reinforcement learning (RL). We show that GPs are KWIK learnable, proving for the first time that a model-based RL approach using GPs, GP-Rmax, is sample efficient (PAC-MDP). However, we then show that previous approaches to model-free RL using GPs take an exponential number of steps to find an optimal policy, and are therefore not sample efficient. The third and main contribution is the introduction of a model-free RL algorithm using GPs, DGPQ, which is sample efficient and, in contrast to model-based algorithms, capable of acting in real time, as demonstrated on a five-dimensional aircraft simulator.},

Author = {Robert Grande and Thomas Walsh and Jonathan How},

Editor = {Tony Jebara and Eric P. Xing},

Year = {2014},

Booktitle = {Proceedings of the 31st International Conference on Machine Learning (ICML-14)},

Pages = {1332-1340}

}