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

By Arishi Orra, Himanshu Choudhary, Manoj Thakur

Published 2026-08-16

Everscope rating

1301

Relevance to quantitative trading

9 / 10

Implementation complexity

8 / 10

Reproducibility

3 / 5

About this paper

Methodology: QUESTrader (Question Enhanced Stock Trader). Problem types: Reinforcement Learning, Portfolio Optimization, Algorithmic Execution, Multi-task Learning, Self-Supervised Learning.

arXiv:2608.15841 · Paper rankings

Open the interactive Everscope explorer for full analysis, charts, and paper battles.