|
Adaptive State Representations For Multi-agent Reinforcement Learning Host Publication: Proceedings of the International Conference on Agents and Artificial Intelligence Authors: Y. De Hauwere, P. Vrancx and A. Nowé Publisher: Scitepress Publication Date: Jan. 2011 Number of Pages: 9 ISBN: 978-989-8425-41-6
Abstract: When multiple agents act in the same environment, single-agent reinforcement learning (RL) techniques often fail, as they do not take into account other agents. An agent using single agent RL generally does not have sufficient information to obtain a good policy. However, multi-agent techniques that simply extend the state space to include information on the other agents suffer from a large overhead, leading to very slow learning. In this paper we describe a multi-level RL algorithm which acts independently whenever possible and learns in which states it should enrich its state information with information about other agents. Such states, which we call conflict states are detected using statistical information about expected payoffs in these states. We demonstrate through experiments that our approach learns a good trade-off between learning in the single- agent state space and learning in the multi-agent state space.
|
