Spinning Up exercises (problem sets 1 and 2)

Implement core pieces of policy-optimization algorithms and diagnose deliberately broken training runs, checked against known-good implementations.

The exercise happens on OpenAI Spinning Up. Canonical link: https://spinningup.openai.com/en/latest/spinningup/exercises.html. Link check: link responded (5 Oct 2026). Opened from this app 0 times; opening is not counted as an attempt.

Supports: RL foundations for research roles; expect some setup work because the code targets older libraries.