Handbook of Markov decision processes : methods and applications

By Eugene A. Feinberg, Adam Shwartz. 2002

353 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Mathematical Modeling for Network Selection in Heterogeneous Wireless Networks — A Tutorial (2013, background): “An MDP is defined through the following objects [50]: a state space S, sets A (s) of available actions at states s ∈ S, transition probabilities ρ(Y |s, a) and reward functions r(s, a) denoting the one-step reward using action a in state s.”
Robustness in Markov Decision Problems with Uncertain Transition Matrices (2003, background): “This may be a difficult task and the estimation errors may have a huge impact on the solution, which is often quite sensitive to changes in the transition probabilities [3].”
Apprenticeship learning using linear programming (2008, unknown): “An equivalent result as Theorem 2 is given in ( Feinberg & Schwartz, 2002 ), p. 178.”
Robust Control of Markov Decision Processes with Uncertain Transition Matrices (2005, background): “…making via a state transition probability matrix, while taking into account the possibility of information gathering and using this information to apply recourse during the multistage decision process (Putterman 1994, Berstsekas and Tsitsiklis 1996, Mine and Osaki 1970, Feinberg and Shwartz 2002).”
Action understanding as inverse planning. (2009, background): “MDPs are a normative framework for modeling sequential decision making under uncertainty, widely used in rational models of human planning and reinforcement learning (Dayan & Daw, 2008), and in real-world applications in operations research and other ﬁelds (Feinberg & Shwartz, 2002; Puterman, 2005).”
Robust Solutions to Markov Decision Problems with Uncertain Transition Matrices (2005, background): “Finite-state and finite-action Markov Decision Processes (MDPs) capture several attractive features that are important in decision-making under uncertainty: they handle risk in se quential decision-making via a state transition probability matrix, while taking into account the possibiUty of informat”