Multi-Agent Reinforcement Learning

MARL is the problem of learning how to make decisions from experience in the presence of multiple other decision making agents.

Standard Reinforcement Learning studies how to build computational agents that can learn how to make decisions from interaction from their environment alone, even without a prior understanding of how that that environment works. This field is closely connected with human and animal learning and uses the idea of rewards obtained implicitely from the environment or explicitely from a trainer.

The field of Multi-Agent Reinforcement Learning has been growing steadily interest and complexity in recent years. This is RL in the more complex situation where there are other agents in the environment to interact with who also impact the reward obtained by our learning agent. Now these other agents could be teammates, oponents or neutral strangers and the learning agent might interact directly or indirectly with them. Game Theory is the study of a particular subset of this problem where the domain is generally well understood and while there may be hidden information which agents may not have access to, the agents do not need to learn about the environment itself in order to take actions.

Our Papers on Multi-Agent Reinforcement Learning

  1. Mean Field MARL
    Decentralized Mean Field Games
    Sriram Ganapathi Subramanian, Matthew Taylor, Mark Crowley, and Pascal Poupart.
    In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI-2022). Virtual. Feb, 2022.
  2. MARLEmpircal
    Investigation of Independent Reinforcement Learning Algorithms in Multi-Agent Environments
    Frontiers in Artificial Intelligence. Sep, 2022.
  3. MARLEmpircal
    Investigation of Independent Reinforcement Learning Algorithms in Multi-Agent Environments
    In NeurIPS 2021 Deep Reinforcement Learning Workshop. Dec, 2021.
  4. PO-MFRL
    Partially Observable Mean Field Reinforcement Learning
    Sriram Ganapathi Subramanian, Matthew Taylor, Mark Crowley, and Pascal Poupart.
    In Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS). International Foundation for Autonomous Agents and Multiagent Systems, London, United Kingdom. May, 2021.
  5. Deep Multi Agent Reinforcement Learning for Autonomous Driving
    Sushrut Bhalla, Sriram Ganapathi Subramanian, and Mark Crowley
    In Canadian Conference on Artificial Intelligence. May, 2020.
  6. Learning Multi-Agent Communication with Reinforcement Learning
    Sushrut Bhalla, Sriram Ganapathi Subramanian, and Mark Crowley
    In Conference on Reinforcement Learning and Decision Making (RLDM-19). Montreal, Canada. 2019.
  7. Training Cooperative Agents for Multi-Agent Reinforcement Learning
    Sushrut Bhalla, Sriram Ganapathi Subramanian, and Mark Crowley
    In Proc. of the 18th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2019). Montreal, Canada. 2019.