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

Authors:
Toshiyuki Yasuda;Kazuhiro Ohkura
Affiliations:
Graduate School of Engineering, Hiroshima University, Hiroshima, Japan 739-8527;Graduate School of Engineering, Hiroshima University, Hiroshima, Japan 739-8527
Venue:
SAB '08 Proceedings of the 10th international conference on Simulation of Adaptive Behavior: From Animals to Animats
Year:
2008

Citing 4
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
Improving search efficiency in the action space of an instance-based reinforcement learning technique for multi-robot systems

ECAL'07 Proceedings of the 9th European conference on Advances in artificial life

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
Reinforcement learning in robotics: A survey

International Journal of Robotics Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

We have developed a new reinforcement learning (RL) technique called Bayesian-discrimination-function-based reinforcement learning (BRL). BRL is unique, in that it does not have state and action spaces designed by a human designer, but adaptively segments them through the learning process. Compared to other standard RL algorithms, BRL has been proven to be more effective in handling problems encountered by multi-robot systems (MRS), which operate in a learning environment that is naturally dynamic. Furthermore, we have developed an extended form of BRL in order to improve the learning efficiency. Instead of generating a random action when a robot functioning within the framework of the standard BRL encounters an unknown situation, the extended BRL generates an action determined by linear interpolation among the rules that have high similarity to the current sensory input. In this study, we investigate the robustness of the extended BRL through further experiments. In both physical experiments and computer simulations, the extended BRL shows higher robustness and relearning ability against an environmental change as compared to the standard BRL.