jgrusewski e8b64a3b24 wip(rl): mask non-done advantages + remove normalization dead code ...

Intermediate state — masked advantages still crash qpa because
distillation + entropy gradients run every step on non-done elements.
Next: two-timescale π update (option 4).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-05-27 00:23:52 +02:00

..

cuda

wip(rl): mask non-done advantages + remove normalization dead code

2026-05-27 00:23:52 +02:00

examples

fix(rl): wire BCE + aux losses into GPU loader path + event-based sync

2026-05-26 22:18:30 +02:00

src

fix(rl): remove advantage normalization — sparse rewards diluted signal

2026-05-27 00:20:27 +02:00

tests

perf(rl): fuse adamw_increment into adamw_step + tau into iqn_forward

2026-05-26 16:46:10 +02:00

build.rs

perf(rl): GPU-resident data loader — zero CPU per step

2026-05-26 20:51:06 +02:00

Cargo.toml

feat(rl): R6 — replace LobEnv with kernel-driven GPU-pure env step

2026-05-23 10:39:25 +02:00