Graph Exploration For Effective Multi-agent Q-learning

Abstract

This paper proposes an exploration technique for multi-agent reinforcement learning (MARL) with graph-based communication among agents. We assume the individual rewards received by the agents are independent of the actions by the other agents, while their policies are coupled. In the proposed framework, neighbouring agents collaborate to estimate the uncertainty about the state-action space in order to execute more efficient explorative behaviour. Different from existing works, the proposed algorithm does not require counting mechanisms and can be applied to continuous-state environments without requiring complex conversion techniques. Moreover, the proposed scheme allows agents to communicate in a fully decentralized manner with minimal information exchange. And for continuous-state scenarios, each agent needs to exchange only a single parameter vector. The performance of the algorithm is verified with theoretical results for discrete-state scenarios and with experiments for continuou

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keyzhaikhan2023graph

Related papers

• Prioritized Guidance For Efficient Multi-agent Reinforcement Learning Exploration (2019)0.00
• MESA: Cooperative Meta-exploration In Multi-agent Learning Through Exploiting State-action Space Structure (2024)2.26
• REMAX: Relational Representation For Multi-agent Exploration (2020)2.26
• Episodic Multi-agent Reinforcement Learning With Curiosity-driven Exploration (2021)0.00
• Provably Efficient Multi-agent Reinforcement Learning With Fully Decentralized Communication (2021)0.00
• Exploiting Semantic Epsilon Greedy Exploration Strategy In Multi-agent Reinforcement Learning (2022)0.00
• Multi-agent Reinforcement Learning In Stochastic Networked Systems (2020)0.00
• Ensemble Value Functions For Efficient Exploration In Multi-agent Reinforcement Learning (2023)0.00