Achieving Mean-Variance Efficiency by Continuous-Time Reinforcement Learning.
Yilie HuangYanwei JiaXun Yu ZhouPublished in: ICAIF (2022)
Keyphrases
- reinforcement learning
- optimal control
- computational complexity
- state space
- machine learning
- learning process
- reinforcement learning algorithms
- computational efficiency
- function approximation
- markov chain
- markov decision processes
- robotic control
- real time
- dynamical systems
- utility function
- evolutionary algorithm
- multi agent systems
- information systems
- real world