Mean-variance optimality for semi-Markov decision processes under first passage criteria.
Xiangxiang HuangYonghui HuangPublished in: Kybernetika (2017)
Keyphrases
- semi markov decision processes
- average reward
- optimality criterion
- markov decision processes
- optimal policy
- long run
- reinforcement learning
- policy iteration
- model free
- question answering
- multi criteria
- utility function
- portfolio selection
- monte carlo
- portfolio optimization
- markov chain
- quasi linear
- language model
- optimal control
- fixed point
- average cost