J
Jerzy A. Filar
Researcher at University of Queensland
Publications - 190
Citations - 4113
Jerzy A. Filar is an academic researcher from University of Queensland. The author has contributed to research in topics: Markov decision process & Hamiltonian path problem. The author has an hindex of 28, co-authored 184 publications receiving 3855 citations. Previous affiliations of Jerzy A. Filar include Johns Hopkins University & University of Maryland, Baltimore County.
Papers
More filters
BookDOI
Competitive Markov decision processes
Jerzy A. Filar,Koos Vrieze +1 more
TL;DR: In this article, the authors present a series of courses and prerequisites for the development of stochastic games with a focus on reducing the complexity of the problem of finding the optimal solution.
Journal ArticleDOI
Algorithms for stochastic games — A survey
T. E. S. Raghavan,Jerzy A. Filar +1 more
TL;DR: Finite state, finite action, stochastic games over an infinite time horizon, algorithms for the computation of minimax optimal stationary strategies in the zerosum case, and of Nash equilibria in stationary Strategies in the nonzerosum case are surveyed.
Journal ArticleDOI
Variance-Penalized Markov Decision Processes
TL;DR: This work considers a Markov decision process with both the expected limiting average, and the discounted total return criteria, appropriately modified to include a penalty for the variability in the stream of rewards.
Journal ArticleDOI
Time consistent dynamic risk measures
Kang Boda,Jerzy A. Filar +1 more
TL;DR: In this paper, the authors introduce the time-consistency concept inspired by the so-called "principle of optimality" of dynamic programming and demonstrate that the conditional value-at-risk (CVaR) need not be timeconsistent in a multi-stage case.
Journal ArticleDOI
Percentile performance criteria for limiting average Markov decision processes
TL;DR: The authors present a complete (and discrete) classification of both the maximal achievable target levels and of their corresponding percentiles and provide an algorithm for computing a deterministic policy corresponding to any feasible target-percentile pair.