The Determination of Approximately Optimal Policies in Markov Decision Processes by the Use of Bounds
From MaRDI portal
Publication:3934167
DOI10.2307/2581490zbMath0477.90082MaRDI QIDQ3934167
Publication date: 1982
Published in: The Journal of the Operational Research Society (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.2307/2581490
Markov decision process; approximately optimal policies; Howard's policy space method; approximation of optimal performance level; derivation of upper and lower bounds
Related Items
Solving infinite horizon discounted Markov decision process problems for a range of discount factors, Approximate receding horizon approach for Markov decision processes: average reward case