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