Data Driven Policy Learning in Real World Multi-Agent Environments

Tutorial To be Presented at 24th European Conference on Artificial Intelligence

Overview of the Tutorial

A fundamental goal of AI is to produce intelligent agents (IAs) that interact with its environment to learn optimal behaviours for autonomous decision making, technically defined as policy learning. Most developments in policy learning algorithms in the past decade have been framed as a Reinforcement Learning (RL) of a single agent, where modelling and predicting behaviour of other agents in the environment is largely unnecessary. Furthermore, the developments are often demonstrated in settings with well-defined utility functions, such as board/video games. However, if AI is to live up to its science-fictional promises to support humanity or even supersede human intelligence, recent algorithmic developments should be scaled to perform in real-world environments where multiple agents interact to accomplish a task. Policy learning in real-world multi-agent environments is extremely complex due to two reasons: (1) The actions of multiple intelligent agents cause the environment to become non-stationary from the perspective of an individual agent. Hence, traditional RL algorithms are not well suited for multi-agent domains. (2) The context of real-world environments is often represented with multiple high-dimensional modalities. In comparison to single agent domains, multi-agent policy learning algorithms suffer from the effects of curse of dimensionality, and high-dimensional context representation further exacerbates this issue. In addition, lack of meaningful data-sets is also partly culpable for comparatively modest progress in the area of multi-agent policy learning. Driverless vehicles (DV), military combat and disaster recovery robots, artificial trading in financial markets, and autonomous communication and language discovery are few ambitious aspirations, where policy learning in multi-agent domains is essential.

Starting with an intuitive explanation of the theoretical underpinnings, this tutorial will present key developments in the area of multi-agent policy learning: namely Multi-agent reinforcement learning and multi-agent imitation learning, which are emerging as key techniques to address the problem of multi agent policy learning. The tutorial will relate to emerging applications of multi-agent policy learning such as driverless vehicle control, sports analytics, urban planning and autonomous generation of video game content. While relating to the real-world applications the tutorial will gently introduce recent attempts at addressing key challenges relate to multi-agent policy learning, such as non-stationarity, communication, selective attention, curriculum learning and generative adversarial policy learning. Furthermore, the discussion will involve, the difference between coordinated learning which is suitable for cooperating agents and learning in the environments where agents compete with each other such as in sports. Tutorial will also introduce the audience to available data sources and experimental platforms to experiment with multi-agent policy learning. Finally, the tutorial will conclude with a discussion on challenges to move theoretical results in the real world applications where agents are required to learn from limited experience.

Target Audience

This tutorial is suitable for anyone with a high level understanding of reinforcement learning, as the session will be pretty intuitive presentation of the algorithms with real world practical examples.

My area of expertise mainly stems from application of the multi-agent learning systems in the real world applications, with a strong focus on driverless car technology and sports analytics. Thus, the tutorial is a synthesis of theoretical ideas directed towards overcoming challenges through scaling up experimental results to real world applications.

P.S. This will NOT be a mathematically rigorous treatment of the MA learning domain, but more of an applied presentation of the research and challenges. This is also NOT a tutorial based upon Game Theory. I hope you understand 90minutes is too short to treat all the fascinating aspects of this beautiful research area.

Prior Reading Material / Previous Tutorials / Important Resources

Here I have provided a list of previous tutorials in the area of Multi-Agent systems and some interesting survey papers of the area.

Recent Survey/Tutorial Papers

  1. Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications [Link to Paper]

  2. Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms [Link to Paper]

  3. A Review of Cooperative Multi-Agent Deep Reinforcement Learning [Link to Paper]

  4. A Survey and Critique of Multiagent Deep Reinforcement Learning [Link to Paper]

Recent Video Tutorials related to Learning in Multi-Agent Systems

You can find my brief biography and my research projects here.

Please dont hesitate to contact me if you have any doubts or questions about this tutorial. You can reach me through email: V.D.De-Silva [at] lboro [dot] ac [dot] uk