mlsanityData to 14 Oct 2026

Self-Supervised Auxiliary Task Discovery for Stable Reinforcement Learning in Stock Trading

arXiv 2608.15841 ↗First posted 16 Aug 2026cs.LG q-fin.CP stat.MLcited by 0

On the map: Deep reinforcement learning methods → Adversarial robustness and RL in finance

Abstract (arXiv)

Reinforcement learning has gained increasing attention as a data-driven approach for stock trading. However, learning a policy that is both profitable and stable remains challenging due to non-stationary market behaviour and noisy reward signals. Auxiliary tasks are often used to improve representation learning and stabilize training, yet they are usually designed manually and depend heavily on prior assumptions about targets and prediction horizons. Such fixed designs may not remain suitable across changing market regimes. In this work, we propose a self-supervised framework that automatically discovers auxiliary tasks to support reinforcement learning for stock trading. The auxiliary tasks are formulated as General Value Functions so that their predictions enrich the learned state representation and assist policy optimization. The framework consists of two networks. The main network learns the trading policy along with the auxiliary predictions, while the secondary network generates the definitions of auxiliary tasks through learned cumulants and discount factors. These tasks are updated using a meta gradient mechanism that accounts for their long-term impact on trading performance and improves training stability. We evaluate the proposed approach across four major equity indices: DJI, FTSE, Sensex, and TAIEX. The empirical results demonstrate that automatically discovered auxiliary tasks lead to more robust learning and improved trading performance compared to existing baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods. Builds on 17 of its 54 references that are in the map. First posted on arXiv 16 Aug 2026.

Builds on

17 of 54 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Deep Reinforcement Learning for Automated Stock Trading: An Ensemble Strategy15 Nov
  2. 2025Deep Reinforcement Learning for Investor-Specific Portfolio Optimization: A Volatility-Guided Asset Selection Approach20 Apr

Other references · 15

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  3. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  4. 2016Reinforcement Learning with Unsupervised Auxiliary Taskscited by 404
  5. 2017A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problemcited by 128
  6. 2019Deep Reinforcement Learning for Tradingcited by 73
  7. 2021FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Financecited by 58
  8. 2018Practical Deep Reinforcement Learning Approach for Stock Tradingcited by 49
  9. 2019Discovery of Useful Questions as Auxiliary Taskscited by 45
  10. 2021Deep Reinforcement Learning in Quantitative Algorithmic Trading: A Reviewcited by 17
  11. 2021DeepScalper: A Risk-Aware Reinforcement Learning Framework to Capture Fleeting Intraday Trading Opportunitiescited by 15
  12. 2022Deep Reinforcement Learning Approach for Trading Automation in The Stock Marketcited by 9
3 more
  1. 2018Adversarial Deep Reinforcement Learning in Portfolio Managementcited by 6
  2. 2023Constructing Time-Series Momentum Portfolios with Deep Multi-Task Learningcited by 5
  3. 2024Improving Deep Reinforcement Learning Agent Trading Performance in Forex using Auxiliary Taskcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Learning Stock Trading Policies via Barycenter-Based Adversarial Inverse Reinforcement Learning
  2. 2026Deep Reinforcement Learning Framework for Diversified Portfolio Management Across Global Equity Markets
  3. 2026Adaptive Regime-Aware Stock Price Prediction Using Autoencoder-Gated Dual Node Transformers with Reinforcement Learning Control
  4. 2023PRUDEX-Compass: Towards Systematic Evaluation of Reinforcement Learning in Financial Markets
  5. 2026Deep Reinforcement Learning for Equity Trading: Benchmarking Actor-Critic Methods with Forward Retraining
  6. 2025A Risk-Aware Reinforcement Learning Reward for Financial Trading
  7. 2025Reinforcement-Learning Portfolio Allocation with Dynamic Embedding of Market Information
  8. 2025Directly Learning Stock Trading Strategies Through Profit Guided Loss Functions