LESSON: Learning to Integrate Exploration Strategies for Reinforcement Learning via an Option Framework

TL;DR

This paper introduces a unified option-critic framework that enables reinforcement learning agents to adaptively combine multiple exploration strategies, improving exploration efficiency across diverse tasks.

Contribution

It presents a novel method for integrating exploration strategies within an option-critic model, allowing adaptive selection tailored to each task.

Findings

Enhanced exploration performance in MiniGrid and Atari environments.

Adaptive strategy selection improves learning efficiency.

Framework outperforms baseline exploration methods.

Abstract

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.