[PDF][PDF] P-MARL: Prediction-Based Multi-Agent Reinforcement Learning for Non-Stationary Environments.

A Marinescu, I Dusparic, A Taylor, V Cahill, S Clarke - AAMAS, 2015 - ifaamas.org
AAMAS, 2015ifaamas.org
ABSTRACT Multi-Agent Reinforcement Learning (MARL) is a widely-used technique for
optimization in decentralised control problems, addressing complex challenges when
several agents change actions simultaneously and without collaboration. Such challenges
are exacerbated when the environment in which the agents learn is inherently non-
stationary, as agents' actions are then non-deterministic. In this paper, we show that
advance knowledge of environment behaviour through prediction significantly improves …
Abstract
Multi-Agent Reinforcement Learning (MARL) is a widely-used technique for optimization in decentralised control problems, addressing complex challenges when several agents change actions simultaneously and without collaboration. Such challenges are exacerbated when the environment in which the agents learn is inherently non-stationary, as agents’ actions are then non-deterministic. In this paper, we show that advance knowledge of environment behaviour through prediction significantly improves agents’ performance in converging to near-optimal control solutions. We propose P-MARL, a MARL approach which employs a prediction mechanism to obtain such advance knowledge, which is then used to improve agents’ learning. The underlying non-stationary behaviour of the environment is modelled as a time-series and prediction is based on historic data and key environment variables. This provides information regarding potential upcoming changes in the environment, which is a key influencer in agents’ decision-making. We evaluate P-MARL in a smart grid scenario and show that a 92% Pareto efficient solution can be achieved in an electric vehicle charging problem, where energy demand across a community of households is inherently non-stationary. Finally, we analyse the effects of environment prediction accuracy on the performance of our approach.
ifaamas.org
以上显示的是最相近的搜索结果。 查看全部搜索结果

Google学术搜索按钮

example.edu/paper.pdf
搜索
获取 PDF 文件
引用
References