Elevator Group Control Using Multiple Reinforcement Learning Agents

Recent algorithmic and theoretical advances in reinforcement learning (RL) have attracted widespread interest. RL algorithmshave appeared that approximatedynamic programming on an incremental basis. They can be trained on the basis of real or simulated experiences, focusing their computation on areas of state space that are actually visited during control, making them computationally tractable on very large problems. If each member of a team of agents employs one of these algorithms, a new collective learning algorithm emerges for the team as a whole. In this paper we demonstratethat such collective RL algorithms can be powerful heuristic methods for addressing large{scale control problems. Elevator group control serves as our testbed. It is a di cult domain posing a combination of challengesnotseenin mostmulti-agentlearningresearchto date. We usea teamof RL agents,each of which is responsible for controlling one elevator car. The team receives a global reinforcement signal which appea...

• Type: Journal
• Year: 1998
• Where: ML
• Authors: Robert H. Crites, Andrew G. Barto
• Keywords: Challengesnotseenin Mostmulti-agentlearningresearchto Date, Collective Rl Algorithms, Elevator Group Control, Machine Learning, ML 1998