Reinforcement Learning: State-of-the-Art

By Marco Wiering

Continous State and Action Spaces.- Relational and First-Order Knowledge Representation.- Hierarchical Approaches.- Predictive Approaches.- Multi-Agent Reinforcement Learning.- Partially Observable Markov Decision Processes (POMDPs).- Decentralized POMDPs (DEC-POMDPs).- Features and Function Approximation.- RL as Supervised Learning (or batch learning).- Bounds and complexity.- RL for Games.- RL in Robotics.- Policy Gradient Techniques.- Least Squares Value Iteration.- Models and Model Induction.- Model-based RL.- Transfer Learning in RL.- Using of and extracting Knowledge in RL.- Biological or Psychological Background.- Evolutionary Approaches.- Closing chapter, prospects, future issues.

• Format: Hardcover
• Language: English
• ISBN: 364227644X
• ISBN13: 9783642276446
• Release Date: March 2012
• Publisher: Springer
• Length: 638 Pages
• Weight: 2.30 lbs.
• Dimensions: 1.5" x 6.2" x 9.2"