Contractivity of Bellman operator in risk averse dynamic programming with infinite horizon.
Milos KopaMartin SmídPublished in: Oper. Res. Lett. (2023)
Keyphrases
- infinite horizon
- risk averse
- dynamic programming
- stochastic programming
- linear program
- inventory level
- risk neutral
- optimal policy
- finite horizon
- optimal control
- utility function
- multistage
- long run
- markov decision processes
- decision makers
- markov decision process
- production planning
- partially observable
- state space
- linear programming
- dec pomdps
- average cost
- fixed cost
- policy iteration
- reinforcement learning
- knapsack problem
- portfolio management
- asymptotically optimal
- data mining
- state dependent
- lost sales