Simulation-Based Optimization: Parametric Optimization Techniques and Reinforcement Learning

By Abhijit Gosavi. 2003

528 citations recorded by the source corpus.

Subfields: Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/7ba47c292d108fc56024a1f82e45d97381342550

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

Citations in the corpus

Pathologies of temporal difference methods in approximate dynamic programming (2010, methodology): “This approach is described in detail in the literature, has been extensively tested in practice, and is one of the major methodologies for approximate DP (see the books by Bertsekas and Tsitsiklis [BeT96], Sutton and Barto [SuB98], Gosavi [ Gos03 ], Cao [Cao07], Chang, Fu, Hu, and Marcus [CFH07], Me”
Algorithms for Reinforcement Learning (2010, background): “Other recent books on the subject include the book of Gosavi (2003) who devotes 60 pages to reinforcement learning algorithms in Chapter 9, concentrating on average cost problems, or that of Cao (2007) who focuses on policy gradient methods.”
LEAD: a methodology for learning efficient approaches to medical diagnosis (2006, background): “Some of the excellent references on RL are [22], [23].”
Application of reinforcement learning to the game of Othello (2008, background): “The reader is referred to [2] [3] [4] [5] for a more extensive discussion of these topics.”
A capacitated facility location problem with constrained backlogging probabilities (2007, methodology): “For a good presentation of the role of simulation in optimisation techniques, refer to the textbook by Gosavi (2003).”
Reinforcement Learning: A Tutorial Survey and Recent Advances (2009, methodology): “Q-P -Learning: Q-P -Learning (Gosavi, 2004b, 2003) follows the scheme of modified PI in which a policy is chosen, its value function is estimated (PE), and using the value function, a better policy is selected (policy improvement).”
Q-learning and enhanced policy iteration in discounted dynamic programming (2010, methodology): “methods have been described in detail in the literature, have been extensively tested in practice, and constitute one of the major methodologies for approximate DP (see the books by Bertsekas and Tsitsiklis [BeT96], Sutton and Barto [SuB98], Gosavi [ Gos03 ], Cao [Cao07], Chang, Fu, Hu, and Marcus [”