An empirical study of policy convergence in Markov decision process value iteration

DOI10.1016/S0305-0548(03)00207-7zbMath1076.90066OpenAlexW2094964720MaRDI QIDQ1886733

William T. Scherer, Christopher W. Zobel

Publication date: 19 November 2004

Published in: Computers \& Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/s0305-0548(03)00207-7

zbMATH Keywords

Markov decision processesDynamic programmingConvergence results

Mathematics Subject Classification ID

Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Related Items

Approximate dynamic programming via direct search in the space of value function approximations

Cites Work

• Unnamed Item
• Unnamed Item
• Dynamic programming and stochastic control
• Geometric bounds for eigenvalues of Markov chains
• The convergence of value iteration in discounted Markov decision processes
• Time will tell: behavioural scoring and the dynamics of consumer credit assessment
• Finding Optimal Survey Policies via Adaptive Markov Decision Processes
• A New Value Iteration method for the Average Cost Dynamic Programming Problem