LESSON: Learning to Integrate Exploration Strategies for Reinforcement Learning via an Option Framework
This addresses the challenge of exploration in RL for agents, though it appears incremental as it builds on existing option-critic models.
The paper tackles the problem of exploration in reinforcement learning by proposing a unified framework that learns to integrate diverse exploration strategies, enabling adaptive selection for effective exploration-exploitation trade-offs, with demonstrated effectiveness in MiniGrid and Atari environments.
In this paper, a unified framework for exploration in reinforcement learning (RL) is proposed based on an option-critic model. The proposed framework learns to integrate a set of diverse exploration strategies so that the agent can adaptively select the most effective exploration strategy over time to realize a relevant exploration-exploitation trade-off for each given task. The effectiveness of the proposed exploration framework is demonstrated by various experiments in the MiniGrid and Atari environments.