Keyphrases
- markov decision processes
- optimal policy
- reinforcement learning
- decision processes
- average cost
- policy iteration
- infinite horizon
- markov decision process
- decision problems
- finite state
- state space
- machine learning
- dynamic programming
- finite horizon
- action space
- partially observable
- decision theoretic planning
- transition matrices
- utility function
- discounted reward
- state abstraction
- risk sensitive
- policy evaluation
- average reward
- objective function
- multistage