[图书][B] Continuous-time Markov decision processes
X Guo, O Hernández-Lerma, X Guo… - 2009 - Springer
In Chap. 2, we formally introduce the concepts associated to a continuous time MDP.
Namely, the basic model of continuous-time MDPs and the concept of a Markov policy are …
Namely, the basic model of continuous-time MDPs and the concept of a Markov policy are …
Constrained-cost adaptive dynamic programming for optimal control of discrete-time nonlinear systems
Q Wei, T Li - IEEE Transactions on Neural Networks and …, 2023 - ieeexplore.ieee.org
For discrete-time nonlinear systems, this research is concerned with optimal control
problems (OCPs) with constrained cost, and a novel value iteration with constrained cost …
problems (OCPs) with constrained cost, and a novel value iteration with constrained cost …
A convex analytic approach to risk-aware Markov decision processes
WB Haskell, R Jain - SIAM Journal on Control and Optimization, 2015 - SIAM
In classical Markov decision process (MDP) theory, we search for a policy that, say,
minimizes the expected infinite horizon discounted cost. Expectation is, of course, a risk …
minimizes the expected infinite horizon discounted cost. Expectation is, of course, a risk …
Continuous time discounted jump Markov decision processes: a discrete-event approach
EA Feinberg - Mathematics of Operations Research, 2004 - pubsonline.informs.org
This paper introduces and develops a new approach to the theory of continuous time jump
Markov decision processes (CTJMDP). This approach reduces discounted CTJMDPs to …
Markov decision processes (CTJMDP). This approach reduces discounted CTJMDPs to …
[图书][B] Finite Approximations in discrete-time stochastic control
Control and optimization of dynamical systems in the presence of stochastic uncertainty is a
mature field with a large range of applications. A comprehensive treatment of such problems …
mature field with a large range of applications. A comprehensive treatment of such problems …
Constrained average cost Markov control processes in Borel spaces
O Hernández-Lerma, J González-Hernández… - SIAM Journal on Control …, 2003 - SIAM
This paper considers constrained Markov control processes in Borel spaces, with
unbounded costs. The criterion to be minimized is a long-run expected average cost, and …
unbounded costs. The criterion to be minimized is a long-run expected average cost, and …
Maximum Causal Entropy Inverse Reinforcement Learning for Mean-Field Games
In this paper, we introduce the maximum casual entropy Inverse Reinforcement Learning
(IRL) problem for discrete-time mean-field games (MFGs) under an infinite-horizon …
(IRL) problem for discrete-time mean-field games (MFGs) under an infinite-horizon …
Sample-path optimality and variance-minimization of average cost Markov control processes
O Hernández-Lerma, O Vega-Amaya… - SIAM Journal on Control …, 1999 - SIAM
This paper studies several average-cost criteria for Markov control processes on Borel
spaces with possibly unbounded costs. Under suitable hypotheses we show (i) the …
spaces with possibly unbounded costs. Under suitable hypotheses we show (i) the …
Discounted continuous-time constrained Markov decision processes in Polish spaces
X Guo, X Song - The Annals of Applied Probability, 2011 - JSTOR
This paper is devoted to studying constrained continuous-time Markov decision processes
(MDPs) in the class of randomized policies depending on state histories. The transition rates …
(MDPs) in the class of randomized policies depending on state histories. The transition rates …
Splitting randomized stationary policies in total-reward Markov decision processes
EA Feinberg, UG Rothblum - Mathematics of Operations …, 2012 - pubsonline.informs.org
This paper studies a discrete-time total-reward Markov decision process (MDP) with a given
initial state distribution. A (randomized) stationary policy can be split on a given set of states …
initial state distribution. A (randomized) stationary policy can be split on a given set of states …