Awesome Multiagent Learning:

A curated list of multiagent learning and related area resources. Inspired by MARL-Papers and awesome-activity-prediction. The papers are sorted by algorithms so far.

Contributing

Welcome to send me email([email protected]) or Pull Request to add links or remove your works.

Overview

• Textbooks
• Tutorials
• Review Papers
• Research Papers
• Platforms

Textbooks

• Multi-Agent Machine Learning: A Reinforcement Approach [Website]
  • H. M. Schwartz, Wiley, 2014
• 多智能體機器學習：強化學習方法
  • 霍華德 M.施瓦兹 著，連曉峰 譯(simplified chinese translation for the above book.)
• Multiagent Systems [Website]
  • G. Weiss, MIT Press, 2013, 2nd edition
• Graph Theoretic Methods in Multi-Agent Networks [Website]
  • M. Mesbahi and M. Egerstedt, Princeton University Press, 2010
• Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations [Website]
  • Y. Shoham, K. Leyton-Brown, Cambridge University Press, 2009
• Distributed Control of Robotic Networks [Website]
  • F. Bullo, J. Cortés, S. Martínez, Princeton University Press 2009
• An Introduction to MultiAgent Systems [Website]
  • M. Wooldridge, John Wiley & Sons, 2009
• Algebraic Graph Theory [Website]
  • C. Godsil and G. Royle, Springer, 2001
• Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence [Website]
  • G. Weiss, The MIT Press, 2000

Tutorials

• SJTU Multi-Agent Reinforcement Learning Tutorial [Website]
  • J. Wang, W. Zhang at SJTU 2018
• Multiagent Learning: Foundations and Recent Trends [Website]
  • S. Albrecht, P. Stone, IJCAI2017
• COMP310: Multi Agent System [Website]
  • T. Payne, 2017-2018
• CompSci 285: Multi-Agent Systems [Website]
  • D. Parkes, 2013
• CS 224M : Multi Agent Systems [Website]
  • Y. Shoham, 2013-14
• Videos for "An Introduction to Multiagent Systems (Second Edition)" [Website]
  • M. Wooldridge, John Wiley & Sons, 2009

Review Papers

• Multiagent learning: Basics, challenges, and prospects [pdf]
  • K. Tuyls, G. Weiss, AI Magazine2012
• A comprehensive survey of multi-agent reinforcement learning [pdf] 8 L. Bus¸oniu, R. Babuska, and B. De Schutter, IIEEE Transactions on Systems Man and Cybernetics Part C Applications and Reviews2008
• Foundations of Multi-Agent Learning [Website]
  • R. Vohra, M. Wellman, AIJ2007
• Cooperative multi-agent learning: The state of the art. [pdf]
  • L. Panait and S. Luke, AAMAS2005
• Learning in Multiagent Systems: An Introduction from a Game-Theoretic Perspective[pdf]
  • J. Vidal, AAMAS2002
• Learning in multi-agent systems [Website]
  • E. Alonso, M. D’Inverno, D. Kudenko, KER2001

Research Papers

Deep Reinforcement Learning

• QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning [arxiv]
  • T. Rashid, M. Samvelyan, C. Witt, ICML2018
• Emergent Complexity via Multi-agent Competition [Paper][Code]
  • T. Bansal, J. Pachocki, S. Sidor, ICLR2018

Counterfactual Policy Gradient

• Counterfactual Multi-Agent policy gradients [arxiv]
  • J. Foerster, G. Farquhar, S. Whiteson
• Stabilising experience replay for deep Multi-Agent reinforcement learning [arxiv]
  • J. Foerster, N. Nardelli, S. Whiteson, ICML2017
• Learning to communicate with deep multi-agent reinforcement learning [paper]
  • J. Foerster, I. Assael, S. Whiteson, NeuralIPS2016

LOLA

• Learning with Opponent-Learning Awareness [paper]
  • J. Foerster, R. Chen, M. Shedivat, Shimon Whiteson, AAMAS2018

DRQN (Deep Recurrent Q Network)

• Recurrent Deep Multiagent Q-Learning for Autonomous Brokers in Smart Grid [paper]
  • Y. Yang, J. Hao, G. Strbac, IJCAI2018
• Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability [arxiv]
  • S. Omidshafiei, J. Pazis, J. Vian, ICML2017
• Deep Recurrent Q-Learning for Partially Observable MDPs [arxiv]
  • M. Hausknecht, P. Stone, AAAI2015

DDPG(Deep Determinstic Policy Gradient)

• Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments [Paper][Code1][Code2]
  • R. Lowe, Y. Wu, A. Tamar, NIPS2017

VDN (Value Decomposition Network)

• Value-Decomposition Networks For Cooperative Multi-Agent Learning [arxiv]
  • P. Sunehag, G. Lever, T. Graepel, AAMAS2018

Q-Learning

Factorized Q-Learning

• Factorized Q-Learning for Large-Scale Multi-Agent Systems [arxiv]
  • Y. Chen, M. Zhou, Y. Wen, AAAI2019

MFMARL

• Mean Field Multi-Agent Reinforcement Learning [arxiv][COde]
  • Y. Yang, R. Luo, M. Li, ICML2018

Fuzzy-Q

• Fuzzy Q-learning [website]
  • P. Glorennec, L. Jouffe, IFSC1997

Correlated-Q

• Correlated Q-learning [pdf]
  • A. Greenwald, K. Hall, ICML2003

Nash-Q

• Nash Q-learning for general-sum stochastic games [pdf]
  • J. Hu, M. Wellman, JMLR2003

Friend or Foe-Q

• Friend-or-foe Q-learning in general-sum games [pdf]
  • M. Littman, ICML2001

Minimax-Q

• Markov games as a framework for multi-agent reinforcement learning [pdf]
  • M. Littman, ICML1994

Joint action Learning

• Reaching pareto-optimality in prisoner’s dilemma using conditional joint action learning [website]
  • D. Banerjee, S. Sen, AAMAS2007
• The dynamics of reinforcement learning in cooperative multiagent systems [pdf]
  • C. Claus, C. Boutilier, AAAI1998

Policy Hill Climbing

• Multiagent learning using a variable learning rate [pdf]
  • M. Bowling, M. Veloso, Artificial Intelligence2002

Learning Automata

Gradient Ascent

Platforms

• Hanabi Learning Environment [Code]
• MAgent [Code]
• multiagent-particle-envs [Code]
• multiagent-competition [Code]

Code for Starcraft: Brood War

• SAIDA [Website]
• TorchCraft [Code]
• Locutus [Code]