Developing, Evaluating and Scaling Learning Agents in Multi-Agent Environments
This work addresses foundational problems in multi-agent systems for researchers, but it is incremental as it primarily reviews and organizes existing research.
The paper tackles the development and evaluation of learning agents in multi-agent environments, summarizing recent work and presenting a taxonomy to highlight open challenges, without providing specific numerical results.
The Game Theory & Multi-Agent team at DeepMind studies several aspects of multi-agent learning ranging from computing approximations to fundamental concepts in game theory to simulating social dilemmas in rich spatial environments and training 3-d humanoids in difficult team coordination tasks. A signature aim of our group is to use the resources and expertise made available to us at DeepMind in deep reinforcement learning to explore multi-agent systems in complex environments and use these benchmarks to advance our understanding. Here, we summarise the recent work of our team and present a taxonomy that we feel highlights many important open challenges in multi-agent research.