Improving search efficiency in the action space of an instance-based reinforcement learning technique for multi-robot systems

Authors:
Toshiyuki Yasuda;Kazuhiro Ohkura
Affiliations:
Graduate School of Engineering, Hiroshima University, Higashi-Hiroshima, Hiroshima, Japan;Graduate School of Engineering, Hiroshima University, Higashi-Hiroshima, Hiroshima, Japan
Venue:
ECAL'07 Proceedings of the 9th European conference on Advances in artificial life
Year:
2007

Citing 3
Cited 2

Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

Machine Learning
Acquisition of Stand-up Behavior by a Real Robot using Hierarchical Reinforcement Learning

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Reinforcement Learning in Continuous Time and Space

Neural Computation

A Reinforcement Learning Technique with an Adaptive Action Generator for a Multi-robot System

SAB '08 Proceedings of the 10th international conference on Simulation of Adaptive Behavior: From Animals to Animats
Instance-based reinforcement learning technique with a meta-learning mechanism for robust multi-robot systems

TAROS'11 Proceedings of the 12th Annual conference on Towards autonomous robotic systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

We have developed a new reinforcement learning technique called Bayesian-discrimination-function-based reinforcement learning (BRL). BRL is unique, in that it not only learns in the predefined state and action spaces, but also simultaneously changes their segmentation. BRL has proven to be more effective than other standard RL algorithms in dealing with multi-robot system (MRS) problems, where the learning environment is naturally dynamic. This paper introduces an extended form of BRL that improves its learning efficiency. Instead of generating a random action when a robot encounters an unknown situation, the extended BRL generates an action calculated by a linear interpolation among the rules with high similarity to the current sensory input. In both physical experiments and computer simulations, the extended BRL showed higher search efficiency than the standard BRL.