An active-set strategy to solve Markov decision processes with good-deal risk measure.
Shu TuBoris DefournyPublished in: Optim. Lett. (2019)
Keyphrases
- markov decision processes
- active set
- efficient implementation
- finite state
- state space
- optimal policy
- reinforcement learning
- transition matrices
- decision theoretic planning
- policy iteration
- average reward
- markov decision process
- dynamic programming
- machine learning
- nonnegative matrix factorization
- reward function
- average cost
- dictionary learning
- markov decision problems
- multistage
- linear combination
- data mining