Overview
What this challenge is about.
You receive 3 years of hourly day-ahead price data and a Python simulator that models state of charge, round-trip efficiency, and a 1-day price forecast with documented uncertainty. Implement A2C with a small MLP for both actor and critic. Train on years 1-2 with random price perturbations and evaluate on year 3 under both perfect-forecast and realistic-uncertainty scenarios. Compare to the LP baseline on (a) net revenue, (b) cycle count, and (c) worst-day P&L. Success is at least a 6 percent revenue uplift under realistic uncertainty with cycle count within 10 percent of the baseline.
The Brief
What you'll do, and what you'll demonstrate.
Train an A2C agent for battery dispatch that beats an LP baseline on net revenue under realistic price uncertainty.
Earning criteria — what you'll demonstrate
- Implement A2C with separate actor and critic networks
- Train and evaluate deep-RL agents on a domain simulator
- Compare RL vs. classical-optimization baselines fairly
- Communicate RL findings to an engineering team accustomed to LP solvers
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
Careers
Roles this prepares you for.
Real titles. Real skill bridges. Pick the one closest to your trajectory.
Machine Learning Engineer
Training and shipping a deep-RL controller against a strong classical baseline is the kind of MLE project that lands offers at industrial-AI startups.
This challenge sharpens
- actor-critic
- a2c
- pytorch
Applied AI Scientist
Comparing deep RL vs. an LP baseline on the right operational metrics is the daily craft of applied AI scientists in energy.
This challenge sharpens
- actor-critic
- policy-evaluation
- energy-modeling
Research Scientist
Multi-seed training, careful uncertainty design, and clear value-function diagnostics are the signals research-scientist hiring teams look for.
This challenge sharpens
- deep-rl
- policy-evaluation
- actor-critic