Codeseys
/

composer-replication-framework

Reinforcement Learning

Model card Files Files and versions

composer-replication-framework / docs /adrs /ADR-010-feature-deletion-datagen.md

Commit History

feat(b4-gpu+b6): GPU train-proof on A10G + docker-gated substrate E2E test

c009712

Codeseys commited on May 29

feat(wave-a): close ADR-011 (SDPO alignment indices) + ADR-012 (review findings)

d02d724

Codeseys commited on May 29

review+fix: cross-family adversarial ADR review (owed item) + remediation

185cce2

Codeseys commited on May 29

feat(datagen): ADR-010 FeatureDeletionEnv synthetic-data subsystem; accepted

9336af3

Codeseys commited on May 29

docs(adr): add ADR-008/009/010 (Dr.GRPO+SDPO, layered hints, FeatureDeletionEnv)

36ab61e

Codeseys commited on May 29