jgrusewski 10e445f2c7 feat(magnitude): advantage standardization in expected_q forward pass — matches loss kernels ...

The forward pass (action selection) must apply the same advantage
standardization as the loss kernels. Otherwise the network's raw
advantages can encode stale C51 preferences that don't match the
standardized training signal.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-08 22:32:59 +02:00

..

backtesting

…

common

fix: switch tracing to stderr (unbuffered) — stdbuf has no effect on Rust

2026-04-02 16:29:55 +02:00

config

…

ctrader-openapi

…

data

…

database

…

market-data

…

ml

feat(magnitude): advantage standardization in expected_q forward pass — matches loss kernels

2026-04-08 22:32:59 +02:00

ml-asset-selection

…

ml-backtesting

…

ml-checkpoint

…

ml-core

cleanup: remove dead bf16 buffers + update FactoredAction docs for 4-branch

2026-04-08 19:52:20 +02:00

ml-data

…

ml-data-validation

…

ml-dqn

cleanup: remove dead bf16 buffers + update FactoredAction docs for 4-branch

2026-04-08 19:52:20 +02:00

ml-ensemble

feat(ensemble): GPU-native ensemble reduce kernel, remove CPU fallbacks

2026-03-29 22:35:37 +02:00

ml-explainability

feat(ensemble): GPU-native ensemble reduce kernel, remove CPU fallbacks

2026-03-29 22:35:37 +02:00

ml-features

test(data): per-file vs global front-month filter — documents quarterly roll bug

2026-04-08 21:31:46 +02:00

ml-hyperopt

refactor: LHS is the correct algorithm for small budgets, not a fallback

2026-03-29 19:18:47 +02:00

ml-labeling

…

ml-observability

…

ml-paper-trading

…

ml-ppo

feat: add PPO CUDA kernels and curiosity inference kernel

2026-03-31 00:39:59 +02:00

ml-regime

…

ml-regime-detection

…

ml-risk

…

ml-security

…

ml-stress-testing

…

ml-supervised

feat(bf16): ml-dqn, ml-ppo, ml-supervised, ml-ensemble, ml-explainability compile clean

2026-03-28 01:51:45 +01:00

ml-universe

…

ml-validation

…

model_loader

…

risk

…

risk-data

…

storage

…

trading_engine

…

trading-data

…

training_uploader

…