scientific article

From MaRDI portal
Publication:3999474

zbMath0725.93082MaRDI QIDQ3999474

Vivek S. Borkar

Publication date: 17 September 1992


Title: zbMATH Open Web Interface contents unavailable due to conflicting licenses.



Related Items

Reinforcement learning, sequential Monte Carlo and the EM algorithmMultiplicative ergodicity and large deviations for an irreducible Markov chain.LP based upper and lower bounds for Cesàro and Abel limits of the optimal values in problems of control of stochastic discrete time systemsMarkov Decision Processes with Variance Minimization: A New Condition and ApproachOptimization problems in chemical reactions using continuous-time Markov chainsCumulative weighting optimizationControlled Markov processes on the infinite planning horizon: Weighted and overtaking cost criteriaConstrained Semi-Markov decision processes with average rewardsDistributed computation of fixed points of \(\infty\)-nonexpansive mapsThe policy iteration algorithm for average continuous control of piecewise deterministic Markov processesSample-Path Optimal Stationary Policies in Stable Markov Decision Chains with the Average Reward CriterionThe Linear Program approach in multi-chain Markov Decision Processes revisitedExtreme Occupation Measures in Markov Decision Processes with an Absorbing StateApproachability in Stackelberg stochastic games with vector costsExact finite approximations of average-cost countable Markov decision processesThe LP approach in average reward MDPs with multiple cost constraints: The countable state caseAnother Set of Conditions for Strongn(n = −1, 0) Discount Optimality in Markov Decision ProcessesSample-path optimality and variance-maximization for Markov decision processesMartingale limit theorem and its application to an ergodic controlled Markov chainA note on the vanishing interest rate approach in average Markov decision chains with continuous and bounded costsMarkov control processes with randomized discounted costQuantitative model-checking of controlled discrete-time Markov processesOn strong average optimality of Markov decision processes with unbounded costsCorrection to: Ergodic and adaptive control of nearest-neighbor motionsAn excursion-theoretic approach to stability of discrete-time stochastic hybrid systemsCompactness of the space of non-randomized policies in countable-state sequential decision processesA further remark on dynamic programming for partially observed Markov processesStopped decision processes in conjunction with general utilityMaximizing the probability of attaining a target prior to extinctionDiscounted Markov decision processes with utility constraintsOccupation measures in average cost Markov decision processesOn the Hamiltonicity Gap and doubly stochastic matricesControlled Markov chains with constraints.Algorithms for optimization and stabilization of controlled Markov chains.Another set of conditions for Markov decision processes with average sample-path costsErgodic control of reflected diffusions with jumpsDenumerable controlled Markov chains with average reward criterion: Sample path optimalityNonzero-Sum Risk-Sensitive Stochastic Games on a Countable State SpaceAverage Reward Markov Decision Processes with Multiple Cost ConstraintsErgodic control of partially observed Markov chainsControlled Sensing for Sequential Multihypothesis Testing with Controlled Markovian Observations and Non-Uniform Control CostOn the General Utility of Discounted Markov Decision ProcessesSample complexity for Markov chain self-tunerThe Expected Total Cost Criterion for Markov Decision Processes under ConstraintsBlackwell optimality in Markov decision processes with partial observation.Empirical Q-Value IterationWhittle indexability in egalitarian processor sharing systems“Controlled” Versions of the Collatz–Wielandt and Donsker–Varadhan FormulaeConstrained Markovian decision processes: The dynamic programming approachConcentration of Contractive Stochastic Approximation and Reinforcement LearningWhittle index based Q-learning for restless bandits with average rewardStrategic measures in optimal control problems for stochastic sequences




This page was built for publication: