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