Table of Contents

Reinforcement Learning.- A Special Issue of Machine Learning on Reinforcement Learning.- Introduction: The Challenge of Reinforcement Learning.- Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning.- Practical Issues in Temporal Difference Learning.- Technical Note: Q-Learning.- Self-Improving Reactive Agents Based on Reinforcement Learning, Planning and Teaching.- Transfer of Learning by Composing Solutions of Elemental Sequential Tasks.- The Convergence of TD(?) for General ?.- A Reinforcement Connectionist Approach to Robot Path Finding in Non-Maze Like Environments.

Promotional Information

Springer Book Archives