Rho-learning: a robotics oriented reinforcement learning algorithm

We present a new reinforcement learning system more suitable to be used in robotics than existing ones. Existing reinforcement learning algorithms are not specifically tailored for robotics and so they do not take advantage of the robotic perception characteristics as well as of the expected complex...

ver descrição completa

Detalhes bibliográficos
Autor: Porta, Josep M.
Formato: otro
Fecha de publicación:2000
País:España
Recursos:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/29985
Acesso em linha:http://hdl.handle.net/10261/29985
Access Level:acceso abierto
Palavra-chave:Reinforcement learning
Robot learning
Sensor relevance
Walking robots
Automation
Robots
Descrição
Resumo:We present a new reinforcement learning system more suitable to be used in robotics than existing ones. Existing reinforcement learning algorithms are not specifically tailored for robotics and so they do not take advantage of the robotic perception characteristics as well as of the expected complexity of the task that robots are likely to face. In a robot, the information about the environment comes from a set of qualitatively different sensors and in the main par of tasks small subsets of these sensors provide enough information to correctly predict the effect of actions. Departing from this analysis, we outline a new reinforcement learning system that aims at determining relevant subsets of sensors for each action and we present an algorithm that partially implements this new reinforcement learning architecture. Results of the application of the algorithm to the problem of learning to walk with a six legged robot are presented and compared with a well known reinforcement learning algorithm (Q-learning) showing the advantages of our approach.