Education choices, longevity and optimal policy in a Ben-Porath economy.
Yukihiro NishimuraPierre PestieauGregory PonthierePublished in: Math. Soc. Sci. (2018)
Keyphrases
- optimal policy
- decision problems
- reinforcement learning
- markov decision processes
- finite horizon
- state space
- dynamic programming
- state dependent
- infinite horizon
- multistage
- sufficient conditions
- long run
- average reward
- finite state
- markov decision process
- bayesian reinforcement learning
- lost sales
- control policies
- serial inventory systems
- asymptotically optimal
- average cost
- decision making
- policy iteration
- partially observable markov decision processes
- sample path
- reward function