Recent Advances in Reinforcement Learning

• Corporate Author: SpringerLink (Online service)
• Other Authors: Kaelbling, Leslie Pack. (Editor)
• Format: Electronic
• Language: English
• Published: Boston, MA : Springer US, 1996.
• Subjects: Computer science.; Artificial intelligence.; Statistical physics.; Dynamical systems.; Computer Science.; Artificial Intelligence (incl. Robotics).; Statistical Physics, Dynamical Systems and Complexity.; Computer Science, general.
• Online Access: View fulltext via EzAccess

Recent Advances in Reinforcement Learning addresses current research in an exciting area that is gaining a great deal of popularity in the Artificial Intelligence and Neural Network communities. Reinforcement learning has become a primary paradigm of machine learning. It applies to problems in which...

Table of Contents:

• Editorial
• Efficient Reinforcement Learning through Symbiotic Evolution
• Linear Least-Squares Algorithms for Temporal Difference Learning
• Feature-Based Methods for Large Scale Dynamic Programming
• On the Worst-Case Analysis of Temporal-Difference Learning Algorithms
• Reinforcement Learning with Replacing Eligibility Traces
• Average Reward Reinforcement Learning: Foundations, Algorithms, and Empirical Results
• The Loss from Imperfect Value Functions in Expectation-Based and Minimax-Based Tasks
• The Effect of Representation and Knowledge on Goal-Directed Exploration with Reinforcement-Learning Algorithms
• Creating Advice-Taking Reinforcement Learners
• Technical Note.