mlsanityData to 14 Oct 2026

Deep Reinforcement Learning for Cryptocurrency Trading: Practical Approach to Address Backtest Overfitting

arXiv 2209.05559 ↗First posted 12 Sep 2022q-fin.ST cs.AI cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Designing profitable and reliable trading strategies is challenging in the highly volatile cryptocurrency market. Existing works applied deep reinforcement learning methods and optimistically reported increased profits in backtesting, which may suffer from the false positive issue due to overfitting. In this paper, we propose a practical approach to address backtest overfitting for cryptocurrency trading using deep reinforcement learning. First, we formulate the detection of backtest overfitting as a hypothesis test. Then, we train the DRL agents, estimate the probability of overfitting, and reject the overfitted agents, increasing the chance of good trading performance. Finally, on 10 cryptocurrencies over a testing period from 05/01/2022 to 06/27/2022 (during which the crypto market crashed two times), we show that the less overfitted deep reinforcement learning agents have a higher return than that of more overfitted agents, an equal weight strategy, and the S&P DBM Index (market benchmark), offering confidence in possible deployment to a real market.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 23 of its 54 references that are in the map. First posted on arXiv 12 Sep 2022.

Builds on

23 of 54 references.

References · 23

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  3. 2016OpenAI Gymcited by 1,736
  4. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  5. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 807
  6. 2017Deep Reinforcement Learning that Matterscited by 754
  7. 2018Tune: A Research Platform for Distributed Model Selection and Trainingcited by 395
  8. 2020Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stoppingcited by 384
  9. 2018Unity: A General Platform for Intelligent Agentscited by 236
  10. 2021Accounting for Variance in Machine Learning Benchmarkscited by 201
  11. 2021Recent Advances in Reinforcement Learning in Financecited by 110
  12. 2018Simple random search provides a competitive approach to reinforcement learningcited by 75
11 more
  1. 2019Deep Reinforcement Learning for Tradingcited by 73
  2. 2021FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Financecited by 58
  3. 2019Measuring the Reliability of Reinforcement Learning Algorithmscited by 51
  4. 2018Practical Deep Reinforcement Learning Approach for Stock Tradingcited by 49
  5. 2016Cryptocurrency Portfolio Management with Deep Reinforcement Learningcited by 32
  6. 2019An intelligent financial portfolio trading strategy using deep Q-learningcited by 14
  7. 2020Modelling and Quantifying Membership Information Leakage in Machine Learningcited by 13
  8. 2021Significant Improvements over the State of the Art? A Case Study of the MS MARCO Document Ranking Leaderboardcited by 12
  9. 2019Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environmentscited by 11
  10. 2021FinRL-Podracer: High Performance and Scalable Deep Reinforcement Learning for Quantitative Financecited by 9
  11. 2021ElegantRL-Podracer: Scalable and Elastic Library for Cloud-Native Deep Reinforcement Learningcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 1; 2025: 0; 2026: 1.

5 papers.

  1. 2023Dynamic Datasets and Market Environments for Financial Reinforcement Learningcited by 15
  2. 2023A Framework for Empowering Reinforcement Learning Agents with Causal Analysis: Enhancing Automated Cryptocurrency Tradingcited by 1
  3. 2024Sustainable broadcasting in Blockchain Networks with Reinforcement Learningcited by 1
  4. 2023An Ensemble Method of Deep Reinforcement Learning for Automated Cryptocurrency Tradingcited by 0
  5. 2026Predictive Extrema, Unprofitable Policies: An AI-Assisted Audit of Candle-Based Binance Spot Timing Modelscited by 0