Non-Stationary Policy Learning for Multi-Timescale Multi-Agent Reinforcement Learning

作者：Patrick Emami, Xiangyu Zhang, David Biagioni, Ahmed S. Zamzam · 年份：2023 · DOI：10.1109/cdc49753.2023.10384223 · 被引用次数：4 · 研究领域：Reinforcement Learning in Robotics、Adaptive Dynamic Programming Control、Model Reduction and Neural Networks

In multi-timescale multi-agent reinforcement learning (MARL), agents interact across different timescales. In general, policies for time-dependent behaviors, such as those induced by multiple timescales, are non-stationary. Learning non-stationary policies is challenging and typically requires sophisticated or inefficient algorithms. Motivated by the prevalence of this control problem in real-world complex systems, we introduce a simple framework for learning non-stationary policies for multi-timescale MARL. Our approach uses available information about agent timescales to define and learn periodic multi-agent policies. In detail, we theoretically demonstrate that the effects of non-stationarity introduced by multiple timescales can be learned by a periodic multi-agent policy. To learn such policies, we propose a policy gradient algorithm that parameterizes the actor and critic with phase-functioned neural networks, which provide an inductive bias for periodicity. The framework's ability to effectively learn multi-timescale policies is validated on a gridworld and building energy management environment.