Simulation-Based Optimization: Parametric Optimization Techniques & Reinforcement Learning Second Edition by Abhijit Gosavi |
• Tutorial
• All the C codes for MDPs, DP, and RL are available here for free download in a zipped format.
• The C code for simultaneous perturbation is available here for free download in zipped format.
• MATLAB codes for DP and RL for MDPs and average reward SMDPs are available here
• A journal paper containing a tutorial available here
You can order the book from Amazon.com by clicking here
Return to the author's website for the book by clicking here