Keyphrases
- optimal policy
- reinforcement learning
- finite horizon
- markov decision processes
- dynamic programming
- state space
- decision problems
- infinite horizon
- decision trees
- state dependent
- long run
- multistage
- finite state
- markov decision process
- average cost
- bayesian reinforcement learning
- average reward
- sufficient conditions
- policy iteration
- control policies
- asymptotically optimal
- lost sales
- reward function