jgrusewski ab3e17f4a2 feat(sp5): Task A2 — Pearl 3 per-branch NoisyNet sigma ...

Per-branch sigma scales with per-branch Q magnitude (v_half from Pearl 1's
ATOM_V_HALF, populated in A1). SIGMA_FRACTION adapts via entropy-deficit
controller targeting 70% of max action entropy (target_entropy =
log(n_actions[b]) * 0.7).

8 ISV slots (NOISY_SIGMA[210..214), SIGMA_FRACTION[214..218)). Reuses
BRANCH_ENTROPY (218..222) from Task A1's q_branch_stats_kernel.

producer_step_scratch_buf grew 103 -> 111 (8 new outputs). wiener_state_buf
already at 543 (A1 sized for entire SP5 block).

NoisyLinear consumer migration deferred to Layer B.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-05-01 21:16:11 +02:00

..

backtesting

cleanup: declarative rewrites for deferred-work TODOs across ml crates

2026-04-23 08:35:27 +02:00

common

plan5(task2): A.4 regression-detection hard-stop on 2N consecutive error-band

2026-04-26 11:49:14 +02:00

config

…

ctrader-openapi

…

data

build: per-package CGU + dep dedup — workspace builds ~30% faster

2026-05-01 01:00:52 +02:00

database

…

market-data

…

ml

feat(sp5): Task A2 — Pearl 3 per-branch NoisyNet sigma

2026-05-01 21:16:11 +02:00

ml-asset-selection

…

ml-backtesting

…

ml-checkpoint

cleanup: declarative rewrites for deferred-work TODOs across ml crates

2026-04-23 08:35:27 +02:00

ml-core

feat(dqn-v2): Plan 4 Task 1A — feature-group index ranges for VSN/attention consumers

2026-04-25 17:31:38 +02:00

ml-data

…

ml-data-validation

…

ml-dqn

fix(dqn): reset gradient_collapse_counter + training_steps at fold boundary (A.3)

2026-04-29 19:43:34 +02:00

ml-ensemble

…

ml-explainability

feat(explainability): post-hoc IG diagnostic CLI for DQN checkpoints

2026-04-23 10:35:48 +02:00

ml-features

cleanup: declarative rewrites for deferred-work TODOs across ml crates

2026-04-23 08:35:27 +02:00

ml-hyperopt

cleanup: declarative rewrites for deferred-work TODOs across ml crates

2026-04-23 08:35:27 +02:00

ml-labeling

…

ml-observability

…

ml-paper-trading

…

ml-ppo

cleanup: rename all _bf16 kernel functions and variables — pure f32 pipeline

2026-04-18 10:19:12 +02:00

ml-regime

…

ml-regime-detection

…

ml-risk

…

ml-security

…

ml-stress-testing

…

ml-supervised

Merge: GPU Bernoulli dropout in supervised Mamba2 (ghost-feature fix)

2026-04-23 10:09:15 +02:00

ml-universe

…

ml-validation

…

model_loader

…

risk

cleanup: declarative rewrites for ml-tests and trading-engine TODOs

2026-04-23 08:44:05 +02:00

risk-data

…

storage

…

trading_engine

cleanup: declarative rewrites for ml-tests and trading-engine TODOs

2026-04-23 08:44:05 +02:00

trading-data

…

training_uploader

…