Overview
What this challenge is about.
Implement A2C for energy-storage dispatch using price data and a Python simulator, then compare to an LP baseline. Earn a verifiable certificate.
The scenario
The operator (around 60 staff, EUR 4.2B assets under management) considers 6 percent revenue uplift on the battery worth roughly EUR 1.4M per year per site; a positive finding would justify a fleet-wide rollout study.
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.
Aligned coursework coming soon.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Actor Critic
Apply actor critic to solve real industry problems and demonstrate production-level capability.
- A2c
Apply a2c to solve real industry problems and demonstrate production-level capability.
- Deep Rl
Apply deep rl to solve real industry problems and demonstrate production-level capability.
- Policy Evaluation
Apply policy evaluation to solve real industry problems and demonstrate production-level capability.
- Pytorch
Apply pytorch to solve real industry problems and demonstrate production-level capability.
- Energy Modeling
Apply energy modeling 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:
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