Isaac009 / MARL-Resources

Useful Multi-agent RL resources

MARL-Resources

General Issues

1. RIIT: Rethinking the Importance of Implementation Tricks in Multi-Agent Reinforcement Learning [Paper].

Paper with code

1. Multi-agent Papers with code Implemetations [Paper].

Useful Multi-agent RL (Cooperation and Communication) resources

2022

1. Efficient Distributed Framework for Collaborative Multi-Agent Reinforcement Learning [Paper].
2. HAVEN: Hierarchical Cooperative Multi-Agent Reinforcement Learning with Dual Coordination Mechanism [Paper].
3. Towards a Standardised Performance Evaluation Protocol for Cooperative MARL [Paper].
4. Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps [Paper].
5. Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel [Paper].
6. Learning Practical Communication Strategies in Cooperative Multi-Agent Reinforcement Learning [Paper].
7. An Analysis of Discretization Methods for Communication Learning with Multi-Agent Reinforcement Learning [Paper].
8. Multi-Agent Reinforcement Learning as a Computational Tool for Language Evolution Research: Historical Context and Future Challenges [Paper]
9. Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel [Paper]
10. A Survey of Multi-Agent Reinforcement Learning with Communication [Paper]

2021

1. The Surprising Effectiveness of MAPPO in Cooperative, Multi-Agent Games [Paper].
2. The Partially Observable Asynchronous Multi-Agent Cooperation Challenge [Paper].
3. Learning to Simulate Self-Driven Particles System with Coordinated Policy Optimization [Paper].
4. Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents [Paper].
5. Heterogeneous Graph Attention Networks for Learning Diverse Communication [Paper].
6. Optimal communication and control strategies in a multi-agent MDP problem [Paper].
7. Learning Emergent Discrete Message Communication for Cooperative Reinforcement Learning [Paper].
8. Multi-agent Communication with Graph Information Bottleneck under Limited Bandwidth [Paper].
9. Communication-Efficient Split Learning Based on Analog Communication and Over the Air Aggregation [Paper].
10. The emergence of visual semantics through communication games [Paper].
11. Minimizing Communication while Maximizing Performance in Multi-Agent Reinforcement Learning [Paper].
12. Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel [Paper].
13. Learning to Improve Representations by Communicating About Perspectives [Paper].
14. Learning to Ground Multi-Agent Communication with Autoencoders [Paper].
15. Optimal communication and control strategies in a multi-agent MDP problem [Paper]
16. A Meta-Gradient Approach to Learning Cooperative Multi-Agent Communication Topology[Paper]
17. Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control [Paper]

2020

1. Deep Multi-Agent Reinforcement Learning for Decentralized Continuous Cooperative Control [Paper].
2. Networked Multi-Agent Reinforcement Learning with Emergent Communication [Paper].
3. Learning to Communicate and Correct Pose Errors [Paper].
4. When2com: Multi-Agent Perception via Communication Graph Grouping [Paper].
5. Learning to Communicate Using Counterfactual Reasoning [Paper].
6. "LazImpa": Lazy and Impatient neural agents learn to communicate efficiently [Paper].
7. Task-Based Information Compression for Multi-Agent Communication Problems with Channel Rate Constraints [Paper].
8. Event-Triggered Multi-agent Reinforcement Learning with Communication under Limited-bandwidth Constraint [Paper].

2019

1. Decentralization of Multiagent Policies by Learning What to Communicate [Paper].
2. Learning to Communicate in a Noisy Environment [Paper].
3. Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control [Paper].
4. Learning Efficient Multi-agent Communication: An Information Bottleneck Approach [Paper].
5. A perspective on multi-agent communication for information fusion [Paper].
6. Anti-efficient encoding in emergent communication [Paper].
7. Fast Adaptation via Meta Learning in Multi-agent Cooperative Tasks [Paper].

2018

1. Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes [Paper].
2. Learning to Communicate: A Machine Learning Framework for Heterogeneous Multi-Agent Robotic Systems [Paper].

2016

1. Learning Multiagent Communication with Backpropagation [Paper].
2. Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks [Paper].

2005

1. Cooperative Multi-Agent Learning: The State of the Art [Paper].

Thesis

Reviews/Survey

1. A Review of Cooperative Multi-Agent Deep Reinforcement Learning [Paper].
2. Causal Multi-Agent Reinforcement Learning: Review and Open Problems [Paper].
3. A Survey of Multi-Agent Reinforcement Learning with Communication [Paper].
4. Learning to Communicate in Multi-Agent Reinforcement Learning : A Review [Paper].