Multi-objective reward generalization: improving performance of Deep Reinforcement Learning for applications in single-asset trading
Open Access
- 5 October 2023
- journal article
- research article
- Published by Springer Nature in Neural Computing and Applications
- Vol. 36 (2) , 619-637
Abstract
We investigate the potential of Multi-Objective, Deep Reinforcement Learning for stock and cryptocurrency single-asset trading: in particular, we consider a Multi-Objective algorithm which generalizes the reward functions and discount factor (i.e., these components are not specified a priori, but incorporated in the learning process). Firstly, using several important assets (BTCUSD, ETHUSDT, XRPUSDT, AAPL, SPY, NIFTY50), we verify the reward generalization property of the proposed Multi-Objective algorithm, and provide preliminary statistical evidence showing increased predictive stability over the corresponding Single-Objective strategy. Secondly, we show that the Multi-Objective algorithm has a clear edge over the corresponding Single-Objective strategy when the reward mechanism is sparse (i.e., when non-null feedback is infrequent over time). Finally, we discuss the generalization properties with respect to the discount factor. The entirety of our code is provided in open-source format.Keywords
Funding Information
- Austrian Science Fund (F65)
- Horizon 2020 (754411)
- Österreichische Forschungsförderungsgesellschaft
- Österreichische Forschungsförderungsgesellschaft
- Università degli Studi di Trieste
This publication has 32 references indexed in Scilit:
- Intelligent trading of seasonal effects: A decision support algorithm based on reinforcement learningDecision Support Systems, 2014
- Reinforcement learning in robotics: A surveyThe International Journal of Robotics Research, 2013
- Heterogeneous trading strategies with adaptive fuzzy Actor–Critic reinforcement learning: A behavioral approachJournal of Economic Dynamics and Control, 2010
- Quality Assessment of Pareto Set Approximations2008
- A Multiagent Approach to $Q$-Learning for Daily Stock TradingIEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 2007
- Adaptive stock trading with dynamic asset allocation using reinforcement learningInformation Sciences, 2006
- An automated FX trading system using adaptive reinforcement learningExpert Systems with Applications, 2006
- Three Automated Stock-Trading Agents: A Comparative StudyLecture Notes in Computer Science, 2006
- A Multi-agent Q-learning Framework for Optimizing Stock Trading Systems2002
- Computational learning techniques for intraday FX trading using popular technical indicatorsIEEE Transactions on Neural Networks, 2001