Solvency Markov Decision Processes with Interest.
Tomás BrázdilTaolue ChenVojtech ForejtPetr NovotnýAistis SimaitisPublished in: CoRR (2013)
Keyphrases
- markov decision processes
- finite state
- optimal policy
- state space
- reinforcement learning
- planning under uncertainty
- policy iteration
- finite horizon
- reachability analysis
- decision theoretic planning
- decision processes
- infinite horizon
- risk sensitive
- dynamic programming
- average reward
- partially observable
- reinforcement learning algorithms
- markov decision process
- transition matrices
- model based reinforcement learning
- state and action spaces
- average cost
- markov chain
- discounted reward
- semi markov decision processes
- action space
- machine learning
- interval estimation