20 epochs × 64 episodes × 200 timesteps = ~62 min per test on H100
with GPU experience collector enabled. Reduce to 10 epochs (~31 min)
to leave headroom for the remaining test suites within the 120-min
workflow deadline. Assertions remain equivalent (5% loss reduction,
Q-value divergence, checkpoint round-trip, walk-forward validation).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>