Keyphrases
- markov decision processes
- transition matrices
- infinite horizon
- policy iteration
- policy evaluation
- optimal policy
- finite horizon
- markov decision process
- dynamic programming
- state space
- finite state
- average cost
- average reward
- stationary policies
- markov decision problems
- partially observable
- reinforcement learning
- planning under uncertainty
- optimal control
- discounted reward
- decision making
- reinforcement learning algorithms
- long run
- decision processes
- reward function
- action space
- markov models
- sufficient conditions
- linear programming
- search space