Neural Networks and Q-Learning for Robotics - Aix-Marseille Université Access content directly
Conference Papers Year : 1999

Neural Networks and Q-Learning for Robotics

Abstract

Introduction Behavior-Based Approach Supervised Learning of a Behavior Miniature Mobile Robot Khepera Illustration: Reward-Penalty Learning Reinforcement Learning Genetic Algorithms Learning Classifier Systems GA & ANN Q-learning Evaluation Function Algorithm Reinforcement Function Update Function Convergence Limitations Generalization Neural Implementations of the Q-learning Multilayer Perceptron Implementation (ideal & Q-CON) Q-KOHON Comparison Knowledge Incorporation Reinforcement Function Design Building of a non-explicit Model Learning in Cooperative Robotics References
Touzet_IJCNN_Tut.pdf (1.02 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-01355056 , version 1 (22-08-2016)

Identifiers

  • HAL Id : hal-01355056 , version 1

Cite

Claude Touzet. Neural Networks and Q-Learning for Robotics. IJCNN’99 (International Joint Conference (IEEE INNS) on Neural Networks), Jul 1999, Washington DC, United States. ⟨hal-01355056⟩

Collections

CNRS UNIV-AMU LNIA
81 View
539 Download

Share

Gmail Mastodon Facebook X LinkedIn More