Keyphrases
- optimal policy
- markov decision processes
- state space
- infinite horizon
- decision problems
- reinforcement learning
- finite horizon
- dynamic programming
- finite state
- state dependent
- long run
- multistage
- training data
- average reward
- sufficient conditions
- lost sales
- bayesian reinforcement learning
- serial inventory systems
- dynamic programming algorithms
- initial state
- policy iteration
- cost function
- multi agent
- average cost
- markov decision process
- machine learning
- semi markov decision processes
- average reward reinforcement learning