Published on Tue Apr 07 2020

An Application of Deep Reinforcement Learning to Algorithmic Trading

Thibaut Théate, Damien Ernst

This scientific research paper presents an innovative approach based on deep reinforcement learning (DRL) to solve the algorithmic trading problem of determining the optimal trading position at any point in time. It proposes a novel DRL trading strategy so as to maximizing the resulting Sharpe ratio performance indicator.

1
7
31
Abstract

This scientific research paper presents an innovative approach based on deep reinforcement learning (DRL) to solve the algorithmic trading problem of determining the optimal trading position at any point in time during a trading activity in stock markets. It proposes a novel DRL trading strategy so as to maximise the resulting Sharpe ratio performance indicator on a broad range of stock markets. Denominated the Trading Deep Q-Network algorithm (TDQN), this new trading strategy is inspired from the popular DQN algorithm and significantly adapted to the specific algorithmic trading problem at hand. The training of the resulting reinforcement learning (RL) agent is entirely based on the generation of artificial trajectories from a limited set of stock market historical data. In order to objectively assess the performance of trading strategies, the research paper also proposes a novel, more rigorous performance assessment methodology. Following this new performance assessment approach, promising results are reported for the TDQN strategy.

Mon May 31 2021
Machine Learning
Deep Reinforcement Learning in Quantitative Algorithmic Trading: A Review
Deep Reinforcement Learning agents proved to be to a force to be reckon with in many complex games like Chess and Go. We can look at the stock market historical price series and movements as a complex imperfect information environment in which we try to maximize return and minimize risk.
15
131
673
Mon Jan 18 2021
Machine Learning
Deep Reinforcement Learning for Active High Frequency Trading
First end-to-end Deep Reinforcement Learning (DRL) based on active high frequency trading. Training is performed on three contiguous months of high-frequency Limit Order Book data.
1
46
161
Tue May 18 2021
Machine Learning
Application of deep reinforcement learning for Indian stock trading automation
Theory of deep reinforcement learning is applied for stock trading strategy and investment decisions to Indian markets. The experiments are performed with three classical Deep Reinforcement Learning models.
3
3
14
Wed Feb 26 2020
Neural Networks
Using Reinforcement Learning in the Algorithmic Trading Problem
Trading on the stock exchange is interpreted into a game with a Markov property consisting of states, actions, and rewards. The best architecture demonstrated a trading strategy for the RTS Index futures(MOEX:RTSI) with a profitability of 66% per year.
1
11
59
Mon Nov 19 2018
Machine Learning
Practical Deep Reinforcement Learning Approach for Stock Trading
We explore the potential of deep reinforcement learning to optimize stock trading strategy and thus maximize investment return. 30 stocks are selected as our trading stocks and their daily prices are used as the training environment. We train a deep reinforcement learning agent and obtain an adaptive trading strategy.
0
0
0
Thu Nov 19 2020
Machine Learning
FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance
The FinRL library allows users to streamline their own developments and compare with existing schemes easily. Within FinRL, virtual environments are configured with stock market datasets, trading agents are trained with neural networks, and extensive backtesting is analyzed via trading performance.
3
11
16
Wed Feb 11 2015
Machine Learning
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Batch Normalization allows us to use much higher learning rates and be less careful about initialization. It also acts as a regularizer, in some cases eliminating the need for Dropout. Applied to a state-of-the-art image classification model, Batch Normalized achieves the same
2
342
1,163
Fri Oct 06 2017
Artificial Intelligence
Rainbow: Combining Improvements in Deep Reinforcement Learning
Deep reinforcement learning community has made several independent improvements to the DQN algorithm. However, it is unclear which of these extensions are complementary and can be fruitfully combined. This paperamines six extensions and empirically studies their combination.
4
3
25
Thu Jul 20 2017
Machine Learning
Proximal Policy Optimization Algorithms
We propose a new family of policy gradient methods for reinforcement learning. They alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent. We show that PPO outperforms other online policy gradient methods.
2
23
5
Wed Jan 25 2017
Machine Learning
Deep Reinforcement Learning: An Overview
We discuss six core elements, six important mechanisms, and 12 applications. We discuss various applications of RL, including games, in particular, AlphaGo. We mention topics not reviewed yet, and list a collection of RL resources.
2
0
3
Fri Nov 20 2015
Machine Learning
Dueling Network Architectures for Deep Reinforcement Learning
Dueling network represents two separate estimators: one for the state value function and one for a state-dependent action. Main benefit of this factoring is to generalize reinforcement learning across actions.
1
0
2
Tue Sep 22 2015
Machine Learning
Deep Reinforcement Learning with Double Q-learning
The popular Q-learning algorithm is known to overestimate action values under certain conditions. We show that the DQN algorithm suffers from substantial overestimations in some games in the Atari 2600 domain.
1
0
2