Pages that link to "Item:Q3688130"

The following pages link to On undiscounted markovian decision processes with compact action spaces (Q3688130):

Displaying 18 items.

• On undiscounted semi-Markov decision processes with absorbing states (Q283987) (← links)
• Policy iteration for continuous-time average reward Markov decision processes in Polish spaces (Q963139) (← links)
• Compactness of the space of non-randomized policies in countable-state sequential decision processes (Q966432) (← links)
• On the existence of relative values for undiscounted Markovian decision processes with a scalar gain rate (Q1080370) (← links)
• Contraction mappings underlying undiscounted Markov decision problems. II (Q1101358) (← links)
• Conditions for existence of average and Blackwell optimal stationary policies in denumerable Markov decision processes (Q1112739) (← links)
• A Brouwer fixed-point mapping approach to communicating Markov decision processes (Q1115361) (← links)
• On compactness of the space of policies in stochastic dynamic programming (Q1122507) (← links)
• Policy iteration type algorithms for recurrent state Markov decision processes (Q1886500) (← links)
• Optimization of a special case of continuous-time Markov decision processes with compact action set (Q2426563) (← links)
• A note on the existence of optimal policies in total reward dynamic programs with compact action sets. (Q2757658) (← links)
• An unbounded Berge's minimum theorem with applications to discounted Markov decision processes (Q2907896) (← links)
• (Q3678994) (← links)
• Time-average optimal constrained semi-Markov decision processes (Q3738958) (← links)
• Counter examples for compact action markov decision chains with average reward criteria (Q3790965) (← links)
• On the Second Optimality Equation for Semi-Markov Decision Models (Q4016704) (← links)
• The Compactness of a Policy Space in Dynamic Programming Via an Extension Theorem for Carathéodory Functions (Q4346231) (← links)
• (Q5054652) (← links)