Keyphrases
- markov decision processes
- state space
- reinforcement learning
- optimal policy
- finite state
- policy iteration
- decision theoretic planning
- planning under uncertainty
- transition matrices
- finite horizon
- reinforcement learning algorithms
- model based reinforcement learning
- dynamic programming
- average reward
- average cost
- decision processes
- partially observable
- factored mdps
- risk sensitive
- action space
- infinite horizon
- state and action spaces
- reachability analysis
- markov decision process
- machine learning
- linear programming
- reward function