Approximate Dynamic Programming and Reinforcement Learning - Algorithms, Analysis and an Application

Approximate Dynamic Programming and Reinforcement Learning - Algorithms, Analysis and an Application

Problems involving optimal sequential making in uncertain dynamic systems arise in domains such as engineering, science and economics. Such problems can often be cast in the framework of Markov Decision Process (MDP). Solving an MDP requires computing the optimal value function and the optimal polic...

Full description

Bibliographic Details
Main Author: Lakshminarayanan, Chandrashekar
Other Authors: Bhatnagar, Shalabh
Language:en_US
Published: 2018
Subjects:
Dynamic Programming (DP)
Reinforcement Learning - Machine Learning
Markov Decision Process (MDP)
Bellman Equation CBE
Machine Learning
Bellman Operator
Crowdsourcing
Approximate Linear Programming (ALP)
Reinforcement Learning
Stochastic Approximation
Approximate Dynamic Programming (ADP)
Approximate Linear Program
Linear Function Approximation (LFA)
Reduced Linear Program (RLP)
Generalized Reduced Linear Program (GRLP)
Crowd Sourcing
Computer Science and Automation
Online Access:http://etd.iisc.ernet.in/2005/3963
http://etd.iisc.ernet.in/abstracts/4850/G27265-Abs.pdf

Internet

http://etd.iisc.ernet.in/2005/3963
http://etd.iisc.ernet.in/abstracts/4850/G27265-Abs.pdf

Similar Items