Using Reinforcement Learning in the Algorithmic Trading Problem (2019-12-01T00:00:00.000000Z)

TL;DR

Trading on the stock exchange is interpreted into a game with a Markov property consisting of states, actions, and rewards and a system for trading the fixed volume of a financial instrument is proposed and experimentally tested based on the asynchronous advantage actor-critic method with the use of several neural network architectures.

Abstract

Abstract—The development of reinforced learning methods has extended application to many areas including algorithmic trading. In this paper trading on the stock exchange is interpreted into a game with a Markov property consisting of states, actions, and rewards. A system for trading the fixed volume of a financial instrument is proposed and experimentally tested; this is based on the asynchronous advantage actor-critic method with the use of several neural network architectures. The application of recurrent layers in this approach is investigated. The experiments were performed on real anonymized data. The best architecture demonstrated a trading strategy for the RTS Index futures (MOEX:RTSI) with a profitability of 66% per annum accounting for commission. The project source code is available via the following link: http://github.com/evgps/a3c_trading.

Authors

I. Oseledets

5 papers

E. Ponomarev

2 papers

A. Cichocki

2 papers

Using Reinforcement Learning in the Algorithmic Trading Problem

TL;DR

Abstract

Authors

References23 items

The Sharpe Ratio

Deep Direct Reinforcement Learning for Financial Signal Representation and Trading

Deep Reinforcement Learning: An Overview

Theoretically-Grounded Policy Advice from Multiple Teachers in Reinforcement Learning Settings with Applications to Negative Transfer

Asynchronous Methods for Deep Reinforcement Learning

Sparse Coding-Inspired Optimal Trading System for HFT Industry

Recurrent Neural Network Regularization

Heterogeneous trading strategies with adaptive fuzzy Actor-Critic reinforcement learning: A behavioral approach

Learning to trade via direct reinforcement

Performance functions and reinforcement learning for trading systems and portfolios

Long Short-Term Memory

The Sharpe Ratio

A direct adaptive method for faster backpropagation learning: the RPROP algorithm

The Theory of Algorithms

A Markovian Decision Process

Review: A. A. Markov, The Theory of Algorithms

Computing Research Repository (CoRR) abs/1701, 1−

RMSProp: Lecture 6a- overview of mini-batch gradient descent COURSERA,

a behavioral approach,” J

Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

Reinforcement Learning: An Introduction

Algorithm Trading using Q-Learning and Recurrent Reinforcement Learning

This Paper Is Included in the Proceedings of the 12th Usenix Symposium on Operating Systems Design and Implementation (osdi '16). Tensorflow: a System for Large-scale Machine Learning Tensorflow: a System for Large-scale Machine Learning

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL

Alternate Names