Hindsight Expectation Maximization for Goal-conditioned Reinforcement Learning

Yunhao Tang, Alp Kucukelbir
Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, PMLR 130:2863-2871, 2021.

Abstract

We propose a graphical model framework for goal-conditioned RL, with an EM algorithm that operates on the lower bound of the RL objective. The E-step provides a natural interpretation of how ’learning in hindsight’ techniques, such as HER, to handle extremely sparse goal-conditioned rewards. The M-step reduces policy optimization to supervised learning updates, which greatly stabilizes end-to-end training on high-dimensional inputs such as images. We show that the combined algorithm, hEM significantly outperforms model-free baselines on a wide range of goal-conditioned benchmarks with sparse rewards.

Cite this Paper

BibTeX
@InProceedings{pmlr-v130-tang21b, title = { Hindsight Expectation Maximization for Goal-conditioned Reinforcement Learning }, author = {Tang, Yunhao and Kucukelbir, Alp}, booktitle = {Proceedings of The 24th International Conference on Artificial Intelligence and Statistics}, pages = {2863--2871}, year = {2021}, editor = {Banerjee, Arindam and Fukumizu, Kenji}, volume = {130}, series = {Proceedings of Machine Learning Research}, month = {13--15 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v130/tang21b/tang21b.pdf}, url = {https://proceedings.mlr.press/v130/tang21b.html}, abstract = { We propose a graphical model framework for goal-conditioned RL, with an EM algorithm that operates on the lower bound of the RL objective. The E-step provides a natural interpretation of how ’learning in hindsight’ techniques, such as HER, to handle extremely sparse goal-conditioned rewards. The M-step reduces policy optimization to supervised learning updates, which greatly stabilizes end-to-end training on high-dimensional inputs such as images. We show that the combined algorithm, hEM significantly outperforms model-free baselines on a wide range of goal-conditioned benchmarks with sparse rewards. } }
Endnote
%0 Conference Paper %T Hindsight Expectation Maximization for Goal-conditioned Reinforcement Learning %A Yunhao Tang %A Alp Kucukelbir %B Proceedings of The 24th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2021 %E Arindam Banerjee %E Kenji Fukumizu %F pmlr-v130-tang21b %I PMLR %P 2863--2871 %U https://proceedings.mlr.press/v130/tang21b.html %V 130 %X We propose a graphical model framework for goal-conditioned RL, with an EM algorithm that operates on the lower bound of the RL objective. The E-step provides a natural interpretation of how ’learning in hindsight’ techniques, such as HER, to handle extremely sparse goal-conditioned rewards. The M-step reduces policy optimization to supervised learning updates, which greatly stabilizes end-to-end training on high-dimensional inputs such as images. We show that the combined algorithm, hEM significantly outperforms model-free baselines on a wide range of goal-conditioned benchmarks with sparse rewards.
APA
Tang, Y. & Kucukelbir, A.. (2021). Hindsight Expectation Maximization for Goal-conditioned Reinforcement Learning . Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 130:2863-2871 Available from https://proceedings.mlr.press/v130/tang21b.html.

Related Material