Pages that link to "Item:Q1969768"

The following pages link to A note on policy algorithms for discounted Markov decision problems (Q1969768):

Displaying 11 items.

• Ranking policies in discrete Markov decision processes (Q622592) (← links)
• A unified approach to Markov decision problems and performance sensitivity analysis with discounted and average criteria: multichain cases (Q705478) (← links)
• On ordinal comparison of policies in Markov reward processes (Q852153) (← links)
• Modified policy iteration algorithms are not strongly polynomial for discounted dynamic programming (Q1785275) (← links)
• An empirical study of policy convergence in Markov decision process value iteration (Q1886733) (← links)
• A note on optimization formulations of Markov decision processes (Q2129661) (← links)
• Policy set iteration for Markov decision processes (Q2350853) (← links)
• Markov control processes with randomized discounted cost (Q2466780) (← links)
• Estimate and approximate policy iteration algorithm for discounted Markov decision models with bounded costs and Borel spaces (Q3119642) (← links)
• Undiscounted Markov decision chains with partial information; an algorithm for computing a locally optimal periodic policy (Q4698113) (← links)
• A New Policy Evaluation Algorithm for Markov Decision Processes with Quasi Birth-Death Structure (Q5462817) (← links)