Keyphrases
- markov decision processes
- state space
- transition matrices
- reinforcement learning
- dynamic programming
- policy iteration
- finite state
- optimal policy
- decision theoretic planning
- average cost
- factored mdps
- finite horizon
- reinforcement learning algorithms
- decision processes
- markov decision process
- infinite horizon
- average reward
- planning under uncertainty
- reachability analysis
- action space
- model based reinforcement learning
- partially observable
- learning algorithm
- semi markov decision processes
- discounted reward
- action sets
- state abstraction
- risk sensitive
- decision diagrams
- initial state
- dynamical systems