Algorithmic trading using continuous action space deep reinforcement learning.
Naseh MajidiMahdi ShamsiFarokh MarvastiPublished in: Expert Syst. Appl. (2024)
Keyphrases
- action space
- reinforcement learning
- state space
- markov decision processes
- state and action spaces
- real valued
- continuous state
- continuous state spaces
- control policies
- reinforcement learning methods
- action selection
- stochastic processes
- function approximators
- continuous action
- state action
- optimal policy
- single agent
- reinforcement learning algorithms
- dynamic programming
- policy search
- reward function
- dynamic environments
- partially observable markov decision processes
- function approximation
- markov decision problems
- supervised learning
- search algorithm
- machine learning