Homepage
»
Welcome
»
About
»
Hosting
General AI
»
Introductions
»
Finite State Machines
»
Ameliorated Future
»
Miscellaneous
Neural Networks
»
Introductions
»
Backpropagation
»
Optimization
»
Simulators
»
Applied NNs
»
Sample Code
»
Image Recognition
»
Image Compression
Artificial Life
»
Tutorials
»
Sample Code
Genetic Algorithms
»
Libraries
»
Sample Code
Fuzzy Logic
»
FAQ
Games
»
Sample Code
Reinforcement Learning
»
Tutorials
»
FAQ
You are in:
Reinforcement Learning
/
FAQ
FAQ
General Questions
What is Reinforcement Learning?
Is RL just trial-and-error learning, or does it include planning?
How does RL relate to Neuro-Dynamic Programming?
What advantages does RL offer on Operations Research problems?
How does RL relate to Neuroscience?
How does RL relate to the psychology of animal behavior?
How does RL relate to behaviorism?
How does RL relate to genetic algorithms?
Who invented RL?
Questions about studying and teaching RL
What sources do you recommend for an introduction to RL?
Where can I find an online version of the Sutton and Barto textbook?
Where can I find the answers to the exercises?
I have found an apparent error in the book. What should I do about it?
How can I obtain an evaluation copy of the book?
Nuts and Bolts of RL
My state and/or action space is huge! Can I still apply RL?
Most RL work assumes the action space is discrete; what about continuous actions?
What about continuous time?
What is the curse of dimensionality?
Isn't tile-coding just grids, and thus subject to the curse of dimensionality?
Why do you call it "tile coding" instead of "CMACs"?
Are RL methods stable with function approximation?
Advice and Opinions
I am doing RL with a backpropagation neural network and it doesn't work, what should I do?
What is the best algorithm to use?
Why do you disparage the term Q-value?
All content copyrighted by Avaye.com