Overview
What this challenge is about.
Train a REINFORCE trading agent on historical stock data, report performance vs. a buy-and-hold baseline, and earn a verifiable certificate.
The scenario
The startup (around 18 staff, pre-Series A research lab) is exploring whether to spin up a quant team; honest negative results are worth more than rosy backtests that overfit history.
The Brief
What you'll do, and what you'll demonstrate.
Train a REINFORCE policy-gradient trading agent and report honest walk-forward performance against a buy-and-hold baseline.
Earning criteria — what you'll demonstrate
- Derive and implement REINFORCE with a baseline in PyTorch
- Design a leak-free walk-forward backtest
- Evaluate RL policies with risk-adjusted metrics, not just returns
- Practice honest reporting of negative or marginal RL results
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Reinforcement Learning
Master · Reinforcement Learning
Strong alignment
This challenge maps to Reinforcement Learning at the Master level. It sharpens the same practical skills your coursework expects — but in a real industry context with actual constraints and deliverables.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Policy Gradients
Apply policy gradients to solve real industry problems and demonstrate production-level capability.
- Reinforce
Apply reinforce to solve real industry problems and demonstrate production-level capability.
- Rl Evaluation
Apply rl evaluation to solve real industry problems and demonstrate production-level capability.
- Backtesting
Apply backtesting to solve real industry problems and demonstrate production-level capability.
- Pytorch
Apply pytorch to solve real industry problems and demonstrate production-level capability.
- Honest Reporting
Apply honest reporting to solve real industry problems and demonstrate production-level capability.
Careers
Career paths this challenge builds toward
Completing this challenge demonstrates skills that transfer directly to these roles:
ML Researcher
Implementing a clean REINFORCE study with honest walk-forward reporting is the kind of integrity-first research that quant + research teams hire for.
This challenge sharpens
- policy-gradients
- reinforce
- honest-reporting
Applied AI Scientist
Risk-adjusted RL evaluation and overfitting analysis is core applied-research work in fintech.
This challenge sharpens
- rl-evaluation
- backtesting
- honest-reporting
Research Scientist
Multi-seed reporting and methodological transparency are the rigor signals industrial research-scientist roles look for.
This challenge sharpens
- policy-gradients
- rl-evaluation
- honest-reporting