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