Representation-Driven Reinforcement Learning

Ofir Nabati, Guy Tennenholtz, Shie Mannor
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25588-25603, 2023.

Abstract

We present a representation-driven framework for reinforcement learning. By representing policies as estimates of their expected values, we leverage techniques from contextual bandits to guide exploration and exploitation. Particularly, embedding a policy network into a linear feature space allows us to reframe the exploration-exploitation problem as a representation-exploitation problem, where good policy representations enable optimal exploration. We demonstrate the effectiveness of this framework through its application to evolutionary and policy gradient-based approaches, leading to significantly improved performance compared to traditional methods. Our framework provides a new perspective on reinforcement learning, highlighting the importance of policy representation in determining optimal exploration-exploitation strategies.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-nabati23a, title = {Representation-Driven Reinforcement Learning}, author = {Nabati, Ofir and Tennenholtz, Guy and Mannor, Shie}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {25588--25603}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/nabati23a/nabati23a.pdf}, url = {https://proceedings.mlr.press/v202/nabati23a.html}, abstract = {We present a representation-driven framework for reinforcement learning. By representing policies as estimates of their expected values, we leverage techniques from contextual bandits to guide exploration and exploitation. Particularly, embedding a policy network into a linear feature space allows us to reframe the exploration-exploitation problem as a representation-exploitation problem, where good policy representations enable optimal exploration. We demonstrate the effectiveness of this framework through its application to evolutionary and policy gradient-based approaches, leading to significantly improved performance compared to traditional methods. Our framework provides a new perspective on reinforcement learning, highlighting the importance of policy representation in determining optimal exploration-exploitation strategies.} }
Endnote
%0 Conference Paper %T Representation-Driven Reinforcement Learning %A Ofir Nabati %A Guy Tennenholtz %A Shie Mannor %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-nabati23a %I PMLR %P 25588--25603 %U https://proceedings.mlr.press/v202/nabati23a.html %V 202 %X We present a representation-driven framework for reinforcement learning. By representing policies as estimates of their expected values, we leverage techniques from contextual bandits to guide exploration and exploitation. Particularly, embedding a policy network into a linear feature space allows us to reframe the exploration-exploitation problem as a representation-exploitation problem, where good policy representations enable optimal exploration. We demonstrate the effectiveness of this framework through its application to evolutionary and policy gradient-based approaches, leading to significantly improved performance compared to traditional methods. Our framework provides a new perspective on reinforcement learning, highlighting the importance of policy representation in determining optimal exploration-exploitation strategies.
APA
Nabati, O., Tennenholtz, G. & Mannor, S.. (2023). Representation-Driven Reinforcement Learning. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:25588-25603 Available from https://proceedings.mlr.press/v202/nabati23a.html.

Related Material