foxhunt

Files

jgrusewski d2d85617be fix: remove stream.synchronize() from graph capture + restore batch_size in apply_to

1. capture_training_graphs had cuStreamSynchronize before begin_capture
   which hung when stream had stale state from experience collection.
2. Training profile apply_to must apply batch_size so smoketest TOML
   (batch_size=64) overrides the conservative default (1024).
3. Removed batch_size from dqn-production.toml — GPU profile is authority.
4. Removed all debug eprints.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-03 01:22:14 +02:00

dqn-hyperopt.toml

feat(generalization): CQL alpha 0.1→1.0, gradient budget 15%→25%

2026-03-29 23:40:30 +02:00

dqn-localdev.toml

fix: GPU training hang — VRAM oversubscription, counterfactual data loss, event leak

2026-04-02 23:08:33 +02:00

dqn-production.toml

fix: remove stream.synchronize() from graph capture + restore batch_size in apply_to

2026-04-03 01:22:14 +02:00

dqn-smoketest.toml

fix: GPU training hang — VRAM oversubscription, counterfactual data loss, event leak