Learning to Communicate with Deep Multi-Agent Reinforcement Learning
This work addresses the challenge of enabling agents to communicate effectively in multi-agent systems, which is incremental as it builds on deep reinforcement learning with novel engineering innovations.
The paper tackles the problem of multiple agents learning communication protocols to maximize shared utility in partially observable environments, demonstrating end-to-end learning of protocols in complex tasks inspired by communication riddles and multi-agent computer vision, with proposed methods RIAL and DIAL achieving successful results in new experimental environments.
We consider the problem of multiple agents sensing and acting in environments with the goal of maximising their shared utility. In these environments, agents must learn communication protocols in order to share information that is needed to solve the tasks. By embracing deep neural networks, we are able to demonstrate end-to-end learning of protocols in complex environments inspired by communication riddles and multi-agent computer vision problems with partial observability. We propose two approaches for learning in these domains: Reinforced Inter-Agent Learning (RIAL) and Differentiable Inter-Agent Learning (DIAL). The former uses deep Q-learning, while the latter exploits the fact that, during learning, agents can backpropagate error derivatives through (noisy) communication channels. Hence, this approach uses centralised learning but decentralised execution. Our experiments introduce new environments for studying the learning of communication protocols and present a set of engineering innovations that are essential for success in these domains.