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