Algorithmic Trading Using Continuous Action Space Deep Reinforcement Learning.
Naseh MajidiMahdi ShamsiFarokh MarvastiPublished in: CoRR (2022)
Keyphrases
- action space
- reinforcement learning
- state space
- markov decision processes
- state and action spaces
- continuous state
- real valued
- continuous state spaces
- action selection
- control policies
- stochastic processes
- function approximators
- markov decision process
- state action
- reinforcement learning algorithms
- function approximation
- single agent
- model free
- markov decision problems
- continuous action
- planning problems
- optimal policy
- higher order
- dynamic programming
- finite state
- policy iteration
- transfer learning
- sufficient conditions
- reinforcement learning methods
- supervised learning
- hidden markov models
- policy search
- image segmentation
- decision making