Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning

Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success. However, given the lack of theoretical insight, it remains unclear what the employed neural networks are learning, or how we should enhance their learning power to address the problems on which...

Resource-constrained Multi-agent Markov Decision Processes

Intelligent autonomous agents, designed to automate and simplify many aspects of our society, will increasingly be required to also interact with other agents autonomously. Where agents interact, they are likely to encounter resource constraints. For example, agents managing household appliances to optimize electricity usage might need to share...

Bottom-up approaches to achieve Pareto optimal agreements in group decision making

In this article, we introduce a new paradigm to achieve Pareto optimality in group decision-making processes: bottom-up approaches to Pareto optimality. It is based on the idea that, while resolving a conflict in a group, individuals may trust some members more than others; thus, they may be willing to cooperate and share more information...

The Representational Capacity of Action-Value Networks for Multi-Agent Reinforcement Learning

Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success. In this work, we empirically investigate the representational power of various network architectures on a series of one-shot games. Despite their simplicity, these games capture many of the crucial...