Percentile performance criteria for limiting average Markov decision processes

DOI10.1109/9.362904MaRDI QIDQ4763758zbMATH OpenOpenAlexFDO

Authors Dmitry Krass, Keith W. Ross, Jerzy Filar

Publication date 7 August 1995

Published in IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL http://hdl.handle.net/2328/26284

zbMATH Keywords

infinite-horizon Markov decision processeslong-run limiting average reward

Mathematics Subject Classification ID

Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Markov and semi-Markov decision processes (90C40) Probabilistic games; gambling (91A60)

Recommendations

• Percentile queries in multi-dimensional Markov decision processes
• Percentile queries in multi-dimensional Markov decision processes
• Percentile Optimization for Markov Decision Processes with Parameter Uncertainty
• Target-level criterion in Markov decision processes
• Markov decision processes associated with two threshold probability criteria

Cited in

(23)

• Time consistent dynamic risk measures
• Percentile queries in multi-dimensional Markov decision processes
• Risk-Sensitive Reinforcement Learning via Policy Gradient Search
• Variance-constrained actor-critic algorithms for discounted and average reward MDPs
• Quantile Markov Decision Processes
• STRONG AVERAGE OPTIMALITY FOR CONTROLLED NONHOMOGENEOUS MARKOV CHAINS^*
• Percentile queries in multi-dimensional Markov decision processes
• Profit criteria involving risk in price setting of virtual products
• Value iteration methods in risk minimizing stopping problems
• Stochastic optimization of forward recursive functions
• Inventory models with minimal service level constraints
• Variance-penalized Markov decision processes: dynamic programming and reinforcement learning techniques
• Stochastic games with lexicographic objectives
• Stochastic games with disjunctions of multiple objectives
• Minimizing risk models in Markov decision processes with policies depending on target values
• Efficient algorithms for risk-sensitive Markov decision processes with limited budget
• Optimal policy for minimizing risk models in Markov decision processes
• Threshold probability of non-terminal type in finite horizon Markov decision processes
• Risk-constrained reinforcement learning with percentile risk criteria
• Optimal threshold probability in undiscounted Markov decision processes with a target set.
• Optimization models for the first arrival target distribution function in discrete time
• Percentile Optimization for Markov Decision Processes with Parameter Uncertainty
• Meet your expectations with guarantees: beyond worst-case synthesis in quantitative games

This page was built for publication: Percentile performance criteria for limiting average Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4763758)