Learning to Communicate in Multi-Agent Reinforcement Learning : A Review
arXiv:1911.05438
Abstract
We consider the issue of multiple agents learning to communicate through reinforcement learning within partially observable environments, with a focus on information asymmetry in the second part of our work. We provide a review of the recent algorithms developed to improve the agents' policy by allowing the sharing of information between agents and the learning of communication strategies, with a focus on Deep Recurrent Q-Network-based models. We also describe recent efforts to interpret the languages generated by these agents and study their properties in an attempt to generate human-language-like sentences. We discuss the metrics used to evaluate the generated communication strategies and propose a novel entropy-based evaluation metric. Finally, we address the issue of the cost of communication and introduce the idea of an experimental setup to expose this cost in cooperative-competitive game.
References in corpus (6)
- Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
- Learning to Communicate with Deep Multi-Agent Reinforcement Learning
- Learning Multiagent Communication with Backpropagation
- Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks
- Emergent Communication through Negotiation
- Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence