Twin-system recurrent reinforcement learning for optimizing portfolio strategy.
Hyungjun ParkMin Kyu SimDong Gu ChoiPublished in: Expert Syst. Appl. (2024)
Keyphrases
- reinforcement learning
- function approximation
- machine learning
- markov decision processes
- autonomous learning
- reinforcement learning algorithms
- artificial neural networks
- learning algorithm
- multi agent
- dynamic programming
- data mining
- feed forward
- objective function
- temporal difference
- decision making
- transaction costs
- stochastic approximation
- exploration strategy
- exploration exploitation tradeoff