Robust Reinforcement Learning (2001)
by
Jun Morimoto
,
Kenji Doya
| Venue: | Advances in Neural Information Processing Systems 13 |
| Citations: | 9 - 2 self |
BibTeX
@INPROCEEDINGS{Morimoto01robustreinforcement,
author = {Jun Morimoto and Kenji Doya},
title = {Robust Reinforcement Learning},
booktitle = {Advances in Neural Information Processing Systems 13},
year = {2001},
pages = {1061--1067},
publisher = {MIT Press}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
This paper proposes a new reinforcement learning (RL) paradigm that explicitly takes into account input disturbance as well as modeling errors. The use of environmental models in RL is quite popular for both off-line learning by simulations and for on-line action planning. However, the difference between the model and the real environment can lead to unpredictable, often unwanted results.
Citations
| 423 | Neuronlike adaptive elements that can solve dicult learning problems - Barto, Sutton, et al. - 1983 |
| 198 | Robust and Optimal Control - Zhou, Doyle, et al. - 1996 |
| 83 | Reinforcement learning in continuous time and space - Doya - 2000 |
| 52 | Reinforcement learning applied to linear quadratic regulation - Bradtke - 1993 |
| 26 | Acquisition of stand-up behavior by a real robot using hierarchical reinforcement learning - Morimoto, Doya - 2007 |
| 1 | Quadratic Games, H1 , and the Riccati Equation - Linear - 1989 |
