Using reward-weighted regression for reinforcement learning of task space control
2007
Conference Paper
am
ei
In this paper, we evaluate different versions from the three main kinds of model-free policy gradient methods, i.e., finite difference gradients, `vanilla' policy gradients and natural policy gradients. Each of these methods is first presented in its simple form and subsequently refined and optimized. By carrying out numerous experiments on the cart pole regulator benchmark we aim to provide a useful baseline for future research on parameterized policy search algorithms. Portable C++ code is provided for both plant and algorithms; thus, the results in this paper can be reevaluated, reused and new algorithms can be inserted with ease.
Author(s): | Peters, J. and Schaal, S. |
Book Title: | Proceedings of the 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning |
Pages: | 262-267 |
Year: | 2007 |
Department(s): | Autonome Motorik, Empirische Inferenz |
Bibtex Type: | Conference Paper (inproceedings) |
DOI: | 10.1109/ADPRL.2007.368197 |
Address: | Honolulu, Hawaii, April 1-5, 2007 |
Cross Ref: | p2672 |
Note: | clmc |
URL: | http://www-clmc.usc.edu/publications/P/peters-ADPRL2007.pdf |
BibTex @inproceedings{Peters_PIISADPRL_2007, title = {Using reward-weighted regression for reinforcement learning of task space control}, author = {Peters, J. and Schaal, S.}, booktitle = {Proceedings of the 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning}, pages = {262-267}, address = {Honolulu, Hawaii, April 1-5, 2007}, year = {2007}, note = {clmc}, crossref = {p2672}, doi = {10.1109/ADPRL.2007.368197}, url = {http://www-clmc.usc.edu/publications/P/peters-ADPRL2007.pdf} } |