This thesis aims to apply the reinforcement learning into soccer robot and show the great power of reinforcement learning for the RoboCup. In the first part, the background of reinforcement learning is briefly introduced before showing the previous work on it. Therefore the difficulty in implementing reinforcement learning is proposed. The second section demonstrates basic concepts in reinforcement learning, including three fundamental elements, state, action and reward respectively, and three classical approaches, dynamic programming, monte carlo methods and temporal-difference learning respectively. When it comes to keepaway framework, more explanations are given to further combine keepaway with reinforcement learning. After the suggestion about sarsa algorithm with two function approximation, artificial neural network and tile coding, it is implemented successfully during the simulations. The results show it significantly improves the performance of soccer robot.


    Access

    Download


    Export, share and cite



    Title :

    Reinforcement Learning in Keepaway Framework for RoboCup Simulation League


    Contributors:
    Li, Wei (author)

    Publication date :

    2011-01-01


    Type of media :

    Theses


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629



    Neural network in computer vision for RoboCup middle size league

    Ribeiro, Paulo Rogério de Almeida / Lopes, Gil / Ribeiro, A. Fernando | BASE | 2016

    Free access

    Distributed active traction control system applied to the RoboCup middle size league

    Almeida, José / Dias, André / Sequeira, João et al. | BASE | 2013

    Free access

    Vision based referee sign language recognition system for the RoboCup MSL league

    Trigueiros, Paulo / Ribeiro, A. Fernando / Reis, L. P. | BASE | 2014

    Free access

    Newton: A High Level Control Humanoid Robot for the RoboCup Soccer KidSize League

    Perico, Danilo H. / Silva, Isaac J. / Vilão Junior, Claudio O. et al. | Springer Verlag | 2015


    Multi-agent system with Policy Gradient Reinforcement Learning for RoboCup Soccer Simulator

    GAVELLI, VIKTOR / GOMEZ,, ALEXANDER | BASE | 2014

    Free access