Keyphrases
- markov decision processes
- transition matrices
- infinite horizon
- average cost
- optimal policy
- average reward
- finite horizon
- finite state
- markov decision process
- dynamic programming
- reinforcement learning
- policy iteration
- state space
- partially observable
- action space
- planning under uncertainty
- stationary policies
- discount factor
- reinforcement learning algorithms
- inventory level
- markov decision problems
- decision making
- initial state
- long run
- steady state
- multistage