Keyphrases
- markov decision processes
- risk sensitive
- finite state
- state space
- optimal policy
- transition matrices
- reinforcement learning
- policy iteration
- dynamic programming
- factored mdps
- finite horizon
- reachability analysis
- decision theoretic planning
- partially observable
- state and action spaces
- decision making
- average reward
- reinforcement learning algorithms
- state abstraction
- action space
- interval estimation
- planning under uncertainty
- average cost
- decision diagrams
- action sets
- discounted reward
- decision theory
- semi markov decision processes
- model based reinforcement learning
- np hard
- bayesian networks