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