TibGM: A Transferable and Information-Based Graphical Model Approach for Reinforcement Learning

Tameem Adel, Adrian Weller
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:71-81, 2019.

Abstract

One of the challenges to reinforcement learning (RL) is scalable transferability among complex tasks. Incorporating a graphical model (GM), along with the rich family of related methods, as a basis for RL frameworks provides potential to address issues such as transferability, generalisation and exploration. Here we propose a flexible GM-based RL framework which leverages efficient inference procedures to enhance generalisation and transfer power. In our proposed transferable and information-based graphical model framework ‘TibGM’, we show the equivalence between our mutual information-based objective in the GM, and an RL consolidated objective consisting of a standard reward maximisation target and a generalisation/transfer objective. In settings where there is a sparse or deceptive reward signal, our TibGM framework is flexible enough to incorporate exploration bonuses depicting intrinsic rewards. We empirically verify improved performance and exploration power.

Cite this Paper


BibTeX
@InProceedings{pmlr-v97-adel19a, title = {{T}ib{GM}: A Transferable and Information-Based Graphical Model Approach for Reinforcement Learning}, author = {Adel, Tameem and Weller, Adrian}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {71--81}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/adel19a/adel19a.pdf}, url = {https://proceedings.mlr.press/v97/adel19a.html}, abstract = {One of the challenges to reinforcement learning (RL) is scalable transferability among complex tasks. Incorporating a graphical model (GM), along with the rich family of related methods, as a basis for RL frameworks provides potential to address issues such as transferability, generalisation and exploration. Here we propose a flexible GM-based RL framework which leverages efficient inference procedures to enhance generalisation and transfer power. In our proposed transferable and information-based graphical model framework ‘TibGM’, we show the equivalence between our mutual information-based objective in the GM, and an RL consolidated objective consisting of a standard reward maximisation target and a generalisation/transfer objective. In settings where there is a sparse or deceptive reward signal, our TibGM framework is flexible enough to incorporate exploration bonuses depicting intrinsic rewards. We empirically verify improved performance and exploration power.} }
Endnote
%0 Conference Paper %T TibGM: A Transferable and Information-Based Graphical Model Approach for Reinforcement Learning %A Tameem Adel %A Adrian Weller %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-adel19a %I PMLR %P 71--81 %U https://proceedings.mlr.press/v97/adel19a.html %V 97 %X One of the challenges to reinforcement learning (RL) is scalable transferability among complex tasks. Incorporating a graphical model (GM), along with the rich family of related methods, as a basis for RL frameworks provides potential to address issues such as transferability, generalisation and exploration. Here we propose a flexible GM-based RL framework which leverages efficient inference procedures to enhance generalisation and transfer power. In our proposed transferable and information-based graphical model framework ‘TibGM’, we show the equivalence between our mutual information-based objective in the GM, and an RL consolidated objective consisting of a standard reward maximisation target and a generalisation/transfer objective. In settings where there is a sparse or deceptive reward signal, our TibGM framework is flexible enough to incorporate exploration bonuses depicting intrinsic rewards. We empirically verify improved performance and exploration power.
APA
Adel, T. & Weller, A.. (2019). TibGM: A Transferable and Information-Based Graphical Model Approach for Reinforcement Learning. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:71-81 Available from https://proceedings.mlr.press/v97/adel19a.html.

Related Material