Application of Episodic Q-Learning to a Multi-agent Cooperative Task
PRICAI '02 Proceedings of the 7th Pacific Rim International Conference on Artificial Intelligence: Trends in Artificial Intelligence
Coordinating Multiple Agents via Reinforcement Learning
Autonomous Agents and Multi-Agent Systems
A contract net based intelligent agent system for solving the reactive hoist scheduling problem
Expert Systems with Applications: An International Journal
A multiagent cooperative learning algorithm
CSCWD'06 Proceedings of the 10th international conference on Computer supported cooperative work in design III
Dealing with errors in a cooperative multi-agent learning system
LAMAS'05 Proceedings of the First international conference on Learning and Adaption in Multi-Agent Systems
Hi-index | 0.00 |
Recently, reinforcement learning has been proposed as an effective method for knowledge acquisition of the multiagent systems. However, most researches on multiagent system applying a reinforcement-learning algorithm focus on the method to reduce complexity due to the existence of multiple agents [4] and goals [8]. Though these predefined structures succeeded in putting down the undesirable effect due to the existence of multiple agents, they would also suppress the desirable emergence of cooperative behaviors in the multiagent domain. We show that the potential cooperative properties among the agent are emerged by means of Profit-sharing [2][3], which is robust in the non-MDPs.