Not Logged In

A Laplacian framework for option discovery in reinforcement learning

Representation learning and option discovery are two of the biggest challenges in reinforcement learning (RL). Proto-value functions (PVFs) are a well-known approach for representation learning in MDPs. In this paper we address the option discovery problem by showing how PVFs implicitly define options. We do it by introducing eigenpurposes, intrinsic reward functions derived from the learned representations. The options discovered from eigenpurposes traverse the principal directions of the state space. They are useful for multiple tasks because they are discovered without taking the environment’s rewards into consideration. Moreover, different options act at different time scales, making them helpful for exploration. We demonstrate features of eigenpurposes in traditional tabular domains as well as in Atari 2600 games.

Citation

M. Machado, M. Bellemare, M. Bowling. "A Laplacian framework for option discovery in reinforcement learning". International Conference on Machine Learning (ICML), (ed: Doina Precup, Yee Whye Teh), pp 2295-2304, August 2017.

Keywords:  
Category: In Conference
Web Links: PMLR

BibTeX

@incollection{Machado+al:ICML17,
  author = {Marlos Machado and Marc Gendron Bellemare and Michael Bowling},
  title = {A Laplacian framework for option discovery in reinforcement
    learning},
  Editor = {Doina Precup, Yee Whye Teh},
  Pages = {2295-2304},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = 2017,
}

Last Updated: October 28, 2020
Submitted by Sabina P

University of Alberta Logo AICML Logo