Constrained Markovian decision processes: The dynamic programming approach
From MaRDI portal
Publication:1593712
DOI10.1016/S0167-6377(00)00039-0zbMath0969.90091MaRDI QIDQ1593712
Xuerong Mao, Aleksey B. Piunovskiy
Publication date: 25 January 2001
Published in: Operations Research Letters (Search for Journal in Brave)
Related Items
Constrained Continuous-Time Markov Control Processes with Discounted Criteria ⋮ Convex analytic approach to constrained discounted Markov decision processes with non-constant discount factors ⋮ Constrained optimality for finite horizon semi-Markov decision processes in Polish spaces ⋮ Markov decision processes with iterated coherent risk measures ⋮ On Bellman's principle with inequality constraints ⋮ An exact iterative search algorithm for constrained Markov decision processes ⋮ Non-randomized policies for constrained Markov decision processes ⋮ Constrained discounted Markov decision processes with Borel state spaces ⋮ Neighbourhood search for constructing Pareto sets
Cites Work
- Stochastic optimal control. The discrete time case
- On dynamic programming: Compactness of the space of policies
- Controlled random sequences: methods of convex analysis and problems with functional constraints
- Constrained Markov Decision Models with Weighted Discounted Rewards
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
