When should agents explore?
Miruna Pislar, David Szepesvari, Georg Ostrovski, Diana L Borsa, Tom Schaul
Abstract
Exploration remains a central challenge for reinforcement learning (RL). Virtually all existing methods share the feature of a *monolithic* behaviour policy that changes only gradually (at best). In contrast, the exploratory behaviours of animals and humans exhibit a rich diversity, namely including forms of *switching* between modes. This paper presents an initial study of mode-switching, non-monolithic exploration for RL. We investigate different modes to switch between, at what timescales it makes sense to switch, and what signals make for good switching triggers. We also propose practical algorithmic components that make the switching mechanism adaptive and robust, which enables flexibility without an accompanying hyper-parameter-tuning burden. Finally, we report a promising initial study on Atari, using two-mode exploration and switching at sub-episodic time-scales.
BibTeX
@inproceedings{
pislar2022when,
title={When should agents explore?},
author={Miruna Pislar and David Szepesvari and Georg Ostrovski and Diana L Borsa and Tom Schaul},
booktitle={International Conference on Learning Representations},
year={2022},
url={https://openreview.net/forum?id=dEwfxt14bca}
}