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