Files
foxhunt/crates
jgrusewski 45eec3f1f2 perf(ci): cap GPU experience collector episodes in integration tests
Reduce per-epoch GPU work from 4M to 12.8K experiences (64 episodes ×
200 timesteps) in CI integration tests. Still exercises the full fused
CUDA kernel (branching+C51+NoisyNets+DSR+fill-sim+N-step) but
completes within CI deadline. Production conservative() defaults
(8192×500) remain untouched.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-13 16:41:47 +01:00
..