Using communication to reduce locality in distributed multiagent learning
- 1 July 1998
- journal article
- research article
- Published by Taylor & Francis in Journal of Experimental & Theoretical Artificial Intelligence
- Vol. 10 (3) , 357-369
- https://doi.org/10.1080/095281398146806
Abstract
This paper attempts to bridge the fields of machine learning, robotics, and distributed AI. It discusses the use of communication in reducing the undesirable effects of locality in fully distributed multi-agent systems with multiple agents robots learning in parallel while interacting with each other. Two key problems, hidden state and credit assignment, are addressed by applying local undirected broadcast communication in a dual role: as sensing and as reinforcement. The methodology is demonstrated on two multi-robot learning experiments. The first describes learning a tightly-coupled coordination task with two robots, the second a loosely-coupled task with four robots learning social rules. Communication is used to (1) share sensory data to overcome hidden state and (2) share reinforcement to overcome the credit assignment problem between the agents and bridge the gap between local individual and global group pay-off.Keywords
This publication has 12 references indexed in Scilit:
- Learning Signaling Behaviors and Specialization in Cooperative AgentsAdaptive Behavior, 1996
- Adaption and Learning in Multi-Agent SystemsPublished by Springer Nature ,1996
- Issues and approaches in the design of collective autonomous agentsRobotics and Autonomous Systems, 1995
- Reward Functions for Accelerated LearningPublished by Elsevier ,1994
- Markov games as a framework for multi-agent reinforcement learningPublished by Elsevier ,1994
- Multi-Agent Reinforcement Learning: Independent vs. Cooperative AgentsPublished by Elsevier ,1993
- Automatic programming of behavior-based robots using reinforcement learningArtificial Intelligence, 1992
- Reinforcement LearningPublished by Springer Nature ,1992
- Active Perception and Reinforcement LearningPublished by Elsevier ,1990
- ?Matched filters? ? neural models of the external worldJournal of Comparative Physiology A, 1987