fix(ml-dqn): migrate branching + regime_conditional — zero candle errors

branching.rs: MlDevice→Arc<CudaStream>, Candle gather/unsqueeze→host-side,
MaybeNoisyLinear::noisy_sigma_slices(), copy_weights via memcpy pattern.

regime_conditional.rs: device→stream field, all GpuTensor ops get &stream,
batch_softmax_actions via host-side Gumbel-max, gradient merge via BTreeMap.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
jgrusewski
2026-03-18 08:06:08 +01:00
parent d6fa11ec6c
commit 2ffaf42197
2 changed files with 688 additions and 1038 deletions

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff