Files
foxhunt/config
jgrusewski d39786df72 feat(reward-v7.1): wire exposure aux gradient with backward GEMM + schedule fixes + dead code cleanup
- Exposure aux kernel -> f32 scratch -> bf16 cast -> backward_fc_layer GEMM
- Weight + bias gradients accumulated into grad_buf (pure GPU, zero CPU sync)
- CEA warmup: linear decay 1.0->base over 25% of epochs
- OFI epoch gate: disabled for first 5 epochs
- Exposure aux decay: base -> 10% over warmup_epochs
- Removed dead v6 fields: loss_aversion, beta_penalty, regret_blend, trade_clustering_penalty
  from ExperienceCollectorConfig (kernel no longer reads them)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-07 23:21:51 +02:00
..