When should agents explore?
This addresses the problem of inefficient exploration in RL for AI agents, offering a novel but incremental improvement over existing methods.
The paper tackles the challenge of monolithic exploration policies in reinforcement learning by introducing mode-switching exploration, which allows agents to switch between diverse exploratory behaviors at sub-episodic timescales. It reports promising results from a detailed analysis on Atari games using a two-mode exploration approach.
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 and detailed analysis on Atari, using two-mode exploration and switching at sub-episodic time-scales.