Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

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

Toussaint Marc, Kontes Georgios, Piperidis Savvas, Vlassis Nikos

Full record


URI: http://purl.tuc.gr/dl/dias/5830B8CA-9579-4734-9AEE-DB24EA53FD55
Year 2009
Type of Item Peer-Reviewed Journal Publication
License
Details
Bibliographic Citation N. 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. https://doi.org/ 10.1007/s10514-009-9132-0
Appears in Collections

Summary

We 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.

Available Files

Services

Statistics