- Original Pdf: pdf
- Keywords: multi-agent reinforcement learning, multi-agent, exploration, intrinsic motivation, MARL, coordinated exploration
- TL;DR: We propose several intrinsic reward functions for encouraging coordinated exploration in multi-agent problems, and introduce an approach to dynamically selecting the best exploration method for a given task, online.
- Abstract: Solving tasks with sparse rewards is one of the most important challenges in reinforcement learning. In the single-agent setting, this challenge has been addressed by introducing intrinsic rewards that motivate agents to explore unseen regions of their state spaces. Applying these techniques naively to the multi-agent setting results in agents exploring independently, without any coordination among themselves. We argue that learning in cooperative multi-agent settings can be accelerated and improved if agents coordinate with respect to what they have explored. In this paper we propose an approach for learning how to dynamically select between different types of intrinsic rewards which consider not just what an individual agent has explored, but all agents, such that the agents can coordinate their exploration and maximize extrinsic returns. Concretely, we formulate the approach as a hierarchical policy where a high-level controller selects among sets of policies trained on different types of intrinsic rewards and the low-level controllers learn the action policies of all agents under these specific rewards. We demonstrate the effectiveness of the proposed approach in a multi-agent gridworld domain with sparse rewards, and then show that our method scales up to more complex settings by evaluating on the VizDoom platform.