Results 281 to 290 of about 35,395 (320)
Some of the next articles are maybe not open access.
Approximations for Partially Observed Markov Decision Processes
2018This chapter studies the finite-model approximation of discrete-time partially observed Markov decision process. We will find that by performing the standard reduction method, where one transforms a partially observed model to a belief-based fully observed model, we can apply and properly generalize the results in the preceding chapters to obtain ...
Saldı, Naci, Linder, T., Yüksel, S.
openaire +2 more sources
Partially Observable Markov Decision Processes and Robotics
Annual Review of Control, Robotics, and Autonomous Systems, 2022Planning under uncertainty is critical to robotics. The partially observable Markov decision process (POMDP) is a mathematical framework for such planning problems. POMDPs are powerful because of their careful quantification of the nondeterministic effects of actions and the partial observability of the states.
openaire +1 more source
Competitive Markov decision processes with partial observation
2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583), 2005We study a class of Markov decision processes (MDPs) in the infinite time horizon where the number of controllers is two and the observation information is allowed to be imperfect. Suppose the system, space and action space are both finite, and the controllers, having conflicting interests with each other, make decisions independently to seek their own
null Shun-Pin Hsu, A. Arapostathis
openaire +1 more source
Structural Results for Partially Observable Markov Decision Processes
Operations Research, 1979This paper examines monotonicity results for a fairly general class of partially observable Markov decision processes. When there are only two actual states in the system and when the actions taken are primarily intended to improve the system, rather than to inspect it, we give reasonable conditions which ensure that the optimal reward function and ...
openaire +1 more source
Partially observable Markov decision processes for artificial intelligence
1995In this paper, we bring techniques from operations research to bear on the problem of choosing optimal actions in partially observable stochastic domains. In many cases, we have developed new ways of viewing the problem that are, perhaps, more consistent with the AI perspective. We begin by introducing the theory of Markov decision processes (Mdps) and
Leslie Pack Kaelbling +2 more
openaire +1 more source
Partially Observed Markov Decision Processes
2016Covering formulation, algorithms, and structural results, and linking theory to real-world applications in controlled sensing (including social learning, adaptive radars and sequential detection), this book focuses on the conceptual foundations of partially observed Markov decision processes (POMDPs).
openaire +1 more source
Partially Observed Markov Decision Processes
Covering formulation, algorithms and structural results and linking theory to real-world applications in controlled sensing (including social learning, adaptive radars and sequential detection), this book focuses on the conceptual foundations of partially observed Markov decision processes (POMDPs).openaire +2 more sources
A Partially Observable Markov Decision Process with Lagged Information
Journal of the Operational Research Society, 1987The paper considers a Markov decision model where instead of the real state S(t) at stage t one observes some state \(S_ c(t)\) at time t and some state \(S_{\ell}(t+1)\) at time \(t+1\) (simultaneously with \(S_ c(t+1))\). The authors tacitly assume some conditional independence between \(S_ c(t)\) and \(S_{\ell}(t+1)\) given S(t), i.e., (1) and (2 ...
KIM, SH Kim, Soung Hie +1 more
openaire +1 more source
Quasi-Deterministic Partially Observable Markov Decision Processes
2009We study a subclass of pomdps, called quasi-deterministic pomdps (qDet- pomdps), characterized by deterministic actions and stochastic observations. While this framework does not model the same general problems as pomdps, they still capture a number of interesting and challenging problems and, in some cases, have interesting properties. By studying the
Camille Besse, Brahim Chaib-draa
openaire +1 more source
Partially Observable Markov Decision Processes and Performance Sensitivity Analysis
IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2008The sensitivity-based optimization of Markov systems has become an increasingly important area. From the perspective of performance sensitivity analysis, policy-iteration algorithms and gradient estimation methods can be directly obtained for Markov decision processes (MDPs).
Yanjie, Li, Baoqun, Yin, Hongsheng, Xi
openaire +2 more sources