Overview
What this challenge is about.
Run PPO alignment on a 7B model with a reward model, evaluate checkpoints for reward and reward-hacking, and recommend the best one to earn a verifiable certificate.
The scenario
The startup (Series A, around 40 staff) is building a customer-service agent platform and needs an honest 'best-checkpoint' methodology for every customer fine-tune; reward-hacked policies have already burned them once.
The Brief
What you'll do, and what you'll demonstrate.
Run PPO RLHF and pick the best checkpoint via held-out human judgement plus reward-hacking diagnostics, not by training reward alone.
Earning criteria — what you'll demonstrate
- Run end-to-end PPO RLHF with a pretrained reward model
- Apply KL-divergence regularization to balance reward and base-model fidelity
- Detect reward-hacking via length, repetition, and KL diagnostics
- Choose the right checkpoint based on multi-metric trade-offs
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.
- Rlhf
Apply rlhf to solve real industry problems and demonstrate production-level capability.
- Ppo
Apply ppo to solve real industry problems and demonstrate production-level capability.
- Reward Hacking
Apply reward hacking to solve real industry problems and demonstrate production-level capability.
- Kl Control
Apply kl control to solve real industry problems and demonstrate production-level capability.
- Model Finetuning
Apply model finetuning to solve real industry problems and demonstrate production-level capability.
- Evaluation
Apply evaluation 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
Running PPO RLHF end-to-end with reward-hacking analysis is the canonical post-training researcher job at AI labs and AI startups in 2024-25.
This challenge sharpens
- rlhf
- ppo
- reward-hacking
AI Safety Researcher
Reward-hacking detection and KL-control discipline are exactly the alignment-research skills safety teams hire for.
This challenge sharpens
- reward-hacking
- kl-control
- rlhf
Research Scientist
Multi-metric checkpoint selection plus methodology write-up is the rigor research-scientist roles look for.
This challenge sharpens
- evaluation
- rlhf
- ppo