Institutional Repository
Technical University of Crete
EN  |  EL



My Space

Learning model-free robot control by a Monte Carlo EM algorithm

Toussaint Marc, Kontes Georgios, Piperidis Savvas, Vlassis Nikos

Simple record

Identifier 10.1007/s10514-009-9132-0-
TitleLearning model-free robot control by a Monte Carlo EM algorithm en
CreatorToussaint Marcen
CreatorKontes Georgiosen
CreatorPiperidis Savvasen
CreatorΠιπεριδης Σαββαςel
CreatorVlassis Nikosen
PublisherSpringer Verlagen
Content SummaryWe address the problem of learning robot control by model-free reinforcement learning (RL). We adopt the probabilistic model of Vlassis and Toussaint (2009) for model-free RL, and we propose a Monte Carlo EM algorithm (MCEM) for control learning that searches directly in the space of controller parameters using information obtained from randomly generated robot trajectories. MCEM is related to, and generalizes, the PoWER algorithm of Kober and Peters (2009). In the finite-horizon case MCEM reduces precisely to PoWER, but MCEM can also handle the discounted infinite-horizon case. An interesting result is that the infinite-horizon case can be viewed as a ‘randomized’ version of the finite-horizon case, in the sense that the length of each sampled trajectory is a random draw from an appropriately constructed geometric distribution. We provide some preliminary experiments demonstrating the effects of fixed (PoWER) vs randomized (MCEM) horizon length in two simulated and one real robot control tasks. en
Type of ItemPeer-Reviewed Journal Publicationen
Type of ItemΔημοσίευση σε Περιοδικό με Κριτέςel
Date of Item2015-03-23-
Date of Publication2009-
SubjectReinforcement learningen
Bibliographic CitationN. Vlassis, M. Toussaint, G. Kontes, and S. Piperidis, "Learning model-free robot control by a Monte Carlo EM algorithm," Autonomous Robots, vol. 27, no. 2, pp. 123-130, 2009.en

Available Files