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

Woojun Kim, Jeonghye Kim, Young-Jin Sung
2/12/2026

No official code found. Best implementation: beanie00/LESSON (6 stars, last commit 2024-09-08).

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.

View on arXivView PDF

Code Implementations(1)

beanie00/LESSONCommunity100%

[ICML 2023] Official code repository for LESSON.

62PythonJul 20, 20232 years ago

Similar Papers

Reinforcement Learning with a Focus on Adjusting Policies to Reach Targets

85% match2024

An Autonomous Non-monolithic Agent with Multi-mode Exploration based on Options Framework

85% match2023

Proximal Policy Optimization with Adaptive Exploration

84% match1 repo102024

A Novel Framework for Uncertainty-Driven Adaptive Exploration

84% match2025

Beyond Optimism: Exploration With Partially Observable Rewards

83% match1 repo52026

Exploration by Random Reward Perturbation

83% match2025

Cite this paper

@article{kim2026lesson,
  title  = {LESSON: Learning to Integrate Exploration Strategies for Reinforcement Learning via an Option Framework},
  author = {Woojun Kim and Jeonghye Kim and Young-Jin Sung},
  year   = {2026},
  eprint = {2310.03342},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/pdf/2310.03342},
  journal = {ICML 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.03342.svg)](https://codeofpaper.com/paper/2310.03342)

Discussion