Keyword

optimality equation

Description: An equation relating the value of a state to its best available action and future value, central to Markov decision process optimization.

Primary topic: Adaptive Dynamic Programming Control (43%)

OpenAlex ID: keywords/optimality-equation

Chapter 8 Markov decision processes

1990 · Martin L. Puterman · Handbooks in operations research and management science · 419

Risk-Sensitive Reinforcement Learning

2002 · Oliver Mihatsch, Ralph Neuneier · Machine Learning · 258

PDF

Optimal control of Boolean control networks with average cost: A policy iteration approach

2018 · Yuhu Wu, Xi-Ming Sun, et al. · Automatica · 190

The policy iteration algorithm for average reward Markov decision processes with general state space

1997 · S.P. Meyn · IEEE Transactions on Automatic Control · 137

Discrete Gambling and Stochastic Games.

1997 · Stephen M. Samuels, Ashok P. Maitra, et al. · Journal of the American Statistical Association · 134

Q-learning and Pontryagin's Minimum Principle

2009 · Prashant Mehta, Sean Meyn · 123

A simple proof for optimality of (s, S) policies in infinite-horizon inventory systems

1991 · Yu-Sheng Zheng · Journal of Applied Probability · 107

Minimizing Risk Models in Markov Decision Processes with Policies Depending on Target Values

1999 · Congbin Wu, Yuanlie Lin · Journal of Mathematical Analysis and Applications · 90

Optimal Design of Sequential Real-Time Communication Systems

2009 · Aditya Mahajan, Demosthenis Teneketzis · IEEE Transactions on Information Theory · 86

Conditions for characterizing the structure of optimal strategies in infinite-horizon dynamic programs

1982 · E. Porteus · Journal of Optimization Theory and Applications · 77

Opportunity-based block replacement

1991 · Rommert Dekker, Eric Smeitink · European Journal of Operational Research · 75

PDF

Partially Observable Total-Cost Markov Decision Processes with Weakly Continuous Transition Probabilities

2016 · Eugene A. Feinberg, Pavlo O. Kasyanov, et al. · Mathematics of Operations Research · 74

PDF

Risk-Sensitive Markov Control Processes

2013 · Yun Shen, Wilhelm Stannat, et al. · SIAM Journal on Control and Optimization · 73

PDF

A novel policy iteration based deterministic Q-learning for discrete-time nonlinear systems

2015 · QingLai Wei, DeRong Liu · Science China Information Sciences · 69

Contraction Conditions for Average and α-Discount Optimality in Countable State Markov Games with Unbounded Rewards

1997 · E. Altman, A. Hordijk, et al. · Mathematics of Operations Research · 66

Denumerable Undiscounted Semi-Markov Decision Processes with Unbounded Rewards

1983 · A. Federgruen, P. J. Schweitzer, et al. · Mathematics of Operations Research · 66

Recurrence conditions for Markov decision processes with Borel state space: A survey

1991 · Onésimo Hernández-Lerma, RaÚl Montes-De-Oca, et al. · Annals of Operations Research · 62

Average, Sensitive and Blackwell Optimal Policies in Denumerable Markov Decision Chains with Unbounded Rewards

1988 · Rommert Dekker, Arie Hordijk · Mathematics of Operations Research · 61

Denumerable state semi-Markov decision processes with unbounded costs, average cost criterion

1979 · A. Federgruen, A. Hordijk, et al. · Stochastic Processes and their Applications · 59

Controlled Markov chains with risk-sensitive criteria: Average cost, optimality equations, and optimal solutions

1999 · Rolando Cavazos-Cadena, Emmanuel Fernández-Gaucherand · Mathematical Methods of Operations Research · 58

The optimality equation in average cost denumerable state semi-Markov decision problems, recurrency conditions and algorithms

1978 · A. Federgruen, H. C. Tijms · Journal of Applied Probability · 58

Stochastic Games with Unbounded Payoffs: Applications to Robust Control in Economics

2011 · Anna Jaśkiewicz, Andrzej S. Nowak · Dynamic Games and Applications · 56

Universally Measurable Policies in Dynamic Programming

1979 · Steven E. Shreve, Dimitri P. Bertsekas · Mathematics of Operations Research · 49

Bias Optimality in Controlled Queueing Systems

1998 · Moshe Haviv, Martin L. Puterman · Journal of Applied Probability · 48

Optimality Conditions for Inventory Control

2016 · Eugene A. Feinberg · 47

PDF

Works count: 451

Citation count: 5,827