Optimal control of Markov processes with incomplete state information

From MaRDI portal

Publication:2521737

Jump to:navigation, search

DOI10.1016/0022-247X(65)90154-XzbMath0137.35803WikidataQ60164368 ScholiaQ60164368MaRDI QIDQ2521737

Karl Johan Åström

Publication date: 1965

Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)

zbMATH Keywords

probability theory

Related Items

Policy structure for discrete time Markov chain disorder problems, How to count and guess well: Discrete adaptive filters, Active inference on discrete state-spaces: a synthesis, Optimal control of jump-linear gaussian systems†, PARTIALLY OBSERVABLE MARKOV DECISION PROCESSES AND PERIODIC POLICIES WITH APPLICATIONS, Performance bounds for discrete-time stochastic optimal control problems†, A survey of algorithmic methods for partially observed Markov decision processes, On the average cost optimality equation and the structure of optimal policies for partially observable Markov decision processes, On the computation of the optimal cost function for discrete time Markov models with partial observations, Rollout approach to sensor scheduling for remote state estimation under integrity attack, A unified model of qualitative belief change: a dynamical systems perspective, Piecewise Linear Approximations for Partially Observable Markov Decision Processes with Finite Horizons, Markov Decision Processes with Incomplete Information and Semiuniform Feller Transition Probabilities, Optimal management of stochastic invasion in a metapopulation with Allee effects, Semi-uniform Feller stochastic kernels, The free energy principle made simpler but not too simple, Deep reinforcement learning for adaptive mesh refinement, Solving zero-sum one-sided partially observable stochastic games, Equivalent conditions for weak continuity of nonlinear filters, Monotone control laws for noisy, countable-state Markov chains, Affect control processes: intelligent affective interaction using a partially observable Markov decision process, Value Iteration is Optic Composition, On Markov chains induced by partitioned transition probability matrices, Partially observable Markov decision model for the treatment of early prostate cancer, Computation of approximate optimal policies in a partially observed inventory model with rain checks, Lumpability in compartmental models, Control: a perspective, State observation accuracy and finite-memory policy performance, Unnamed Item, SWITCHING AND SEQUENCING AVAILABLE THERAPIES SO AS TO MAXIMIZE A PATIENT'S EXPECTED TOTAL LIFETIME, A survey of decision making and optimization under uncertainty, Active Inference, Belief Propagation, and the Bethe Approximation, Unnamed Item, Uniform Fatou's lemma, Planning and acting in partially observable stochastic domains, Non-deterministic weighted automata evaluated over Markov chains, State estimation for partially observed Markov chains, On infinite horizon active fault diagnosis for a class of non-linear non-Gaussian systems, Application of two inequality results for concave functions to a stochastic optimization problem, Finite-state, discrete-time optimization with randomly varying observation quality, On the Bellman principle for decision problems with random decision policies, Probabilistic models for optimizing patients survival rates, Monotonicity properties for two-action partially observable Markov decision processes on partially ordered spaces, Politica optima de produccion y control: Un modelo Markoviano, Separation of estimation and control for decentralized stochastic control systems, Recursive filters for partially observable finite Markov chains, Successive approximations in partially observable controlled Markov chains with risk-sensitive average criterion, Knowledge-based programs as succinct policies for partially observable domains, Analysis of an identification algorithm arising in the adaptive estimation of Markov chains, Bottom-up learning of hierarchical models in a class of deterministic pomdp environments, Optimal stochastic control, Optimal control of Markov processes with incomplete state-information. II: The convexity of the loss-function, Remarks on the existence of solutions to the average cost optimality equation in Markov decision processes, Application of Jensen's inequality to adaptive suboptimal design, An adaptive automaton controller for discrete-time Markov processes, Problems of identification and control, Dual control of an integrator with unknown gain, Partially observable Markov decision processes with imprecise parameters, Monitoring machine operations using on-line sensors, Partially observable environment estimation with uplift inference for reinforcement learning based recommendation, History-dependent Evaluations in Partially Observable Markov Decision Process, A tutorial on partially observable Markov decision processes, Optimizing active surveillance for prostate cancer using partially observable Markov decision processes, Stratified breast cancer follow-up using a continuous state partially observable Markov decision process, Active Inference: Demystified and Compared, Sophisticated Inference, Transformation of partially observable Markov decision processes into piecewise linear ones, A survey of solution techniques for the partially observed Markov decision process, Optimal cost and policy for a Markovian replacement problem, On the undecidability of probabilistic planning and related stochastic optimization problems, Recursive estimation of a discrete-time Markov chain, Optimal sensor scheduling for hidden Markov model state estimation

Cites Work

Retrieved from "https://portal.mardi4nfdi.de/w/index.php?title=Publication:2521737&oldid=15244243"