Fox: Formation-aware Exploration In Multi-agent Reinforcement Learning

Abstract

Recently, deep multi-agent reinforcement learning (MARL) has gained significant popularity due to its success in various cooperative multi-agent tasks. However, exploration still remains a challenging problem in MARL due to the partial observability of the agents and the exploration space that can grow exponentially as the number of agents increases. Firstly, in order to address the scalability issue of the exploration space, we define a formation-based equivalence relation on the exploration space and aim to reduce the search space by exploring only meaningful states in different formations. Then, we propose a novel formation-aware exploration (FoX) framework that encourages partially observable agents to visit the states in diverse formations by guiding them to be well aware of their current formation solely based on their own observations. Numerical results show that the proposed FoX framework significantly outperforms the state-of-the-art MARL algorithms on Google Research Football

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keyjo2023fox

Related papers

• MESA: Cooperative Meta-exploration In Multi-agent Learning Through Exploiting State-action Space Structure (2024)2.26
• Graph Exploration For Effective Multi-agent Q-learning (2023)5.24
• AIR: Unifying Individual And Collective Exploration In Cooperative Multi-agent Reinforcement Learning (2024)0.00
• MARL-LNS: Cooperative Multi-agent Reinforcement Learning Via Large Neighborhoods Search (2024)0.00
• An Empirical Study On Google Research Football Multi-agent Scenarios (2023)6.77
• Prioritized Guidance For Efficient Multi-agent Reinforcement Learning Exploration (2019)0.00
• Ensemble Value Functions For Efficient Exploration In Multi-agent Reinforcement Learning (2023)0.00
• REMAX: Relational Representation For Multi-agent Exploration (2020)2.26