ICLR 2018poster580 citations
Maximum a Posteriori Policy Optimisation
Abbas Abdolmaleki, Jost Tobias Springenberg, Yuval Tassa, Remi Munos, Nicolas Heess, Martin Riedmiller
Abstract
We introduce a new algorithm for reinforcement learning called Maximum a-posteriori Policy Optimisation (MPO) based on coordinate ascent on a relative-entropy objective. We show that several existing methods can directly be related to our derivation. We develop two off-policy algorithms and demonstrate that they are competitive with the state-of-the-art in deep reinforcement learning. In particular, for continuous control, our method outperforms existing methods with respect to sample efficiency, premature convergence and robustness to hyperparameter settings.
Reinforcement LearningVariational InferenceControl
BibTeX
@inproceedings{
abdolmaleki2018maximum,
title={Maximum a Posteriori Policy Optimisation},
author={Abbas Abdolmaleki and Jost Tobias Springenberg and Yuval Tassa and Remi Munos and Nicolas Heess and Martin Riedmiller},
booktitle={International Conference on Learning Representations},
year={2018},
url={https://openreview.net/forum?id=S1ANxQW0b},
}