AIR: Unifying Individual and Collective Exploration in Cooperative Multi-Agent Reinforcement Learning
Not on the map. Why?
Abstract (arXiv)
Exploration in cooperative multi-agent reinforcement learning (MARL) remains challenging for value-based agents due to the absence of an explicit policy. Existing approaches include individual exploration based on uncertainty towards the system and collective exploration through behavioral diversity among agents. However, the introduction of additional structures often leads to reduced training efficiency and infeasible integration of these methods. In this paper, we propose Adaptive exploration via Identity Recognition~(AIR), which consists of two adversarial components: a classifier that recognizes agent identities from their trajectories, and an action selector that adaptively adjusts the mode and degree of exploration. We theoretically prove that AIR can facilitate both individual and collective exploration during training, and experiments also demonstrate the efficiency and effectiveness of AIR across various tasks.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 24 references that are in the map. First posted on arXiv 20 Dec 2024.
Builds on
20 of 24 references.
References · 20
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
- 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 708
- 2017Reinforcement Learning with Deep Energy-Based Policiescited by 669
- 2019The StarCraft Multi-Agent Challengecited by 597
- 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 503
- 2019QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learningcited by 379
- 2020QPLEX: Duplex Dueling Multi-Agent Q-Learningcited by 270
- 2019Google Research Football: A Novel Reinforcement Learning Environmentcited by 260
- 2020Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 197
- 2019MAVEN: Multi-Agent Variational Explorationcited by 185
- 2015Multiagent Cooperation and Competition with Deep Reinforcement Learningcited by 184
- 2020ROMA: Multi-Agent Reinforcement Learning with Emergent Rolescited by 137
8 more
- 2020RODE: Learning Roles to Decompose Multi-Agent Taskscited by 125
- 2021Celebrating Diversity in Shared Multi-Agent Reinforcement Learningcited by 98
- 2020Qatten: A General Framework for Cooperative Multiagent Reinforcement Learningcited by 81
- 2019Influence-Based Multi-Agent Explorationcited by 75
- 2021Rethinking the Implementation Tricks and Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learningcited by 68
- 2021Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Explorationcited by 49
- 2022Spatial-Temporal-Aware Safe Multi-Agent Reinforcement Learning of Connected Autonomous Vehicles in Challenging Scenarioscited by 13
- 2018Multi-vehicle Flocking Control with Deep Deterministic Policy Gradient Methodcited by 7
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Evolutionary Enhanced Multi-Agent Reinforcement Learning for Cooperative Air Combat
- 2025Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration
- 2024MESA: Cooperative Meta-Exploration in Multi-Agent Learning through Exploiting State-Action Space Structure
- 2019Independent Generative Adversarial Self-Imitation Learning in Cooperative Multiagent Systems
- 2025MIR: Efficient Exploration in Episodic Multi-Agent Reinforcement Learning via Mutual Intrinsic Reward
- 2019Multi-Agent Adversarial Inverse Reinforcement Learning
- 2025A Learning Framework For Cooperative Collision Avoidance of UAV Swarms Leveraging Domain Knowledge
- 2025From Solo to Symphony: Orchestrating Multi-Agent Collaboration with Single-Agent Demos