Files
foxhunt/crates
jgrusewski 70f074658f fix(hyperopt): restore best checkpoint for RegimeConditional agent before walk-forward
serialize_model() saves only the trending (primary) head into a single safetensors
blob. The restore code only handled Standard(DQN) and skipped RegimeConditional
with a warning. This caused walk-forward to always evaluate the final epoch model
instead of the best per-epoch Sharpe checkpoint.

Fix: load the checkpoint directly into primary_head_mut() for the RegimeConditional
variant, matching the serialization path.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-12 13:59:31 +01:00
..