A Design of Reward Function Based on Knowledge in Multi-agent Learning

Authors:
Bo Fan;Jiexin Pu
Affiliations:
Electronic Information Engineering College, Henan University of Science & Technology, Luoyang, P.R. China 471003;Electronic Information Engineering College, Henan University of Science & Technology, Luoyang, P.R. China 471003
Venue:
ADMA '08 Proceedings of the 4th international conference on Advanced Data Mining and Applications
Year:
2008

Citing 5
Cited 0

Technical Note: \cal Q-Learning

Machine Learning
Creating advice-taking reinforcement learners

Machine Learning - Special issue on reinforcement learning
Embedding a Priori Knowledge in Reinforcement Learning

Journal of Intelligent and Robotic Systems
Planning, Learning and Coordination in Multiagent Decision Processes

Proceedings of the Sixth Conference on Theoretical Aspects of Rationality and Knowledge
Existence of multiagent equilibria with limited agents

Journal of Artificial Intelligence Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

The design of reward function is the key to build reinforcement learning system. With the analysis and research of the reinforcement learning and Markov games, an improved reward function is presented, which includes both the goal information based on task and learner's action information based on its domain knowledge. According with this reinforcement function, reinforcement learning integrates the external environment reward and the internal behavior reward so that learner can perform better. The results of the experiment illuminates the reward function involving domain knowledge is better than the traditional reward function in application.