Keyphrases
- markov decision processes
- reinforcement learning
- state space
- optimal policy
- dynamic programming
- policy iteration
- stationary policies
- finite state
- planning under uncertainty
- decision theoretic planning
- reinforcement learning algorithms
- reachability analysis
- model based reinforcement learning
- average reward
- transition matrices
- decision processes
- partially observable
- finite horizon
- factored mdps
- action space
- average cost
- reward function
- decision diagrams
- risk sensitive
- infinite horizon
- state and action spaces
- machine learning
- markov decision process
- discounted reward
- decision problems
- semi markov decision processes
- dynamical systems
- np hard
- real time dynamic programming