Optimizing the Pairs-Trading Strategy Using Deep Reinforcement Learning with Trading and Stop-Loss Boundaries.
Taewook KimHa Young KimPublished in: Complex. (2019)
Keyphrases
- reinforcement learning
- electronic commerce
- pairwise
- function approximation
- state space
- model free
- markov decision processes
- temporal difference
- multi agent
- learning algorithm
- transition model
- temporal difference learning
- financial markets
- reinforcement learning algorithms
- dynamic programming
- learning process
- stochastic approximation
- learning agents
- action space
- multi agent reinforcement learning
- robotic control
- candidate pairs
- test bed
- electronic markets
- object boundaries
- data sets
- learning problems
- monte carlo
- active learning
- multi agent systems
- machine learning
- neural network