Modular learning system and scheduling for behavior acquisition in multi-agent environment

Authors:
Yasutake Takahashi;Kazuhiro Edazawa;Minoru Asada
Affiliations:
Emergent Robotics Area, Dept. of Adaptive Machine Systems, Graduate School of Engineering, Osaka University, Osaka, Japan;Emergent Robotics Area, Dept. of Adaptive Machine Systems, Graduate School of Engineering, Osaka University, Osaka, Japan;Emergent Robotics Area, Dept. of Adaptive Machine Systems, Graduate School of Engineering, Osaka University, Osaka, Japan
Venue:
RoboCup 2004
Year:
2005

Citing 6
Cited 0

Transfer of Learning by Composing Solutions of Elemental Sequential Tasks

Machine Learning
Purposive behavior acquisition for a real robot by vision-based reinforcement learning

Machine Learning - Special issue on robot learning
Cooperative behavior acquisition for mobile robots in dynamically changing real worlds via vision-based reinforcement learning and development

Artificial Intelligence - Special issue on Robocop: the first step
Robot Learning

Robot Learning
Adaptive mixtures of local experts

Neural Computation
Reinforcement learning with a hierarchy of abstract models

AAAI'92 Proceedings of the tenth national conference on Artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

The existing reinforcement learning approaches have been suffering from the policy alternation of others in multiagent dynamic environments such as RoboCup competitions since other agent behaviors may cause sudden changes of state transition probabilities of which constancy is necessary for the learning to converge. A modular learning approach would be able to solve this problem if a learning agent can assign each module to one situation in which the module can regard the state transition probabilities as constant. This paper presents a method of modular learning in a multiagent environment, by which the learning agent can adapt its behaviors to the situations as results of the other agent's behaviors. Scheduling for learning is introduced to avoid the complexity in autonomous situation assignment.