Keyphrases
- markov decision processes
- optimal policy
- transition matrices
- finite state
- reinforcement learning
- state space
- finite horizon
- dynamic programming
- decision theoretic planning
- reachability analysis
- policy iteration
- average cost
- partially observable
- factored mdps
- real time dynamic programming
- infinite horizon
- planning under uncertainty
- action space
- average reward
- decision processes
- state abstraction
- markov decision process
- risk sensitive
- reinforcement learning algorithms
- policy evaluation
- decision making
- semi markov decision processes
- long run
- interval estimation