Curiosity-driven Exploration in Sparse-reward Multi-agent Reinforcement Learning

2023/02/21 by Jiong Li, Li, Jiong, Pratik Gajane +1
Psychology · #Artificial Intelligence (cs.AI) #Behavioral Health and Interventions #FOS: Computer and information sciences #Motivation and Self-Concept in Sports

paper · pdf · doi:10.48550/arxiv.2302.10825

openalex publication_date 2023/02/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Sparsity of rewards while applying a deep reinforcement learning method negatively affects its sample-efficiency. A viable solution to deal with the sparsity of rewards is to learn via intrinsic motivation which advocates for adding an intrinsic reward to the reward function to encourage the agent to explore the environment and expand the sample space. Though intrinsic motivation methods are widely used to improve data-efficient learning in the reinforcement learning model, they also suffer from the so-called detachment problem. In this article, we discuss the limitations of intrinsic curiosity module in sparse-reward multi-agent reinforcement learning and propose a method called I-Go-Explore that combines the intrinsic curiosity module with the Go-Explore framework to alleviate the detachment problem.

Related

• Curiosity-Driven Multi-Agent Exploration with Mixed Objectives
• Never Explore Repeatedly in Multi-Agent Reinforcement Learning
• Scheduled Intrinsic Drive: A Hierarchical Take on Intrinsically Motivated Exploration
• Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?
• Dealing with Sparse Rewards in Reinforcement Learning