diff --git a/crates/ml/src/trainers/dqn/state_reset_registry.rs b/crates/ml/src/trainers/dqn/state_reset_registry.rs index dfb113ffb..16154dbf9 100644 --- a/crates/ml/src/trainers/dqn/state_reset_registry.rs +++ b/crates/ml/src/trainers/dqn/state_reset_registry.rs @@ -575,7 +575,7 @@ impl StateResetRegistry { RegistryEntry { name: "sp5_budget_c51", category: ResetCategory::FoldReset, - description: "ISV[BUDGET_C51_BASE=190..194) — per-branch C51 loss budget share. SP7 (2026-05-03): driven by the loss-balance controller using flatness-modulated target ratio (C51/IQN ≤ 1.0×flatness). Pearl A sentinel 0 at fold boundary; consumer-side bootstrap = C51_BOOTSTRAP_BUDGET = 0.05 in fused_training.rs::compute_adaptive_budgets. (Pearl 2 no longer writes this slot post-SP7.)", + description: "ISV[BUDGET_C51_BASE=190..194) — per-branch C51 loss budget share. SP7 (2026-05-03): will be driven by the loss-balance controller using flatness-modulated target ratio (C51/IQN ≤ 1.0×flatness). Pearl A sentinel 0 at fold boundary; consumer-side floor currently 0.05 (`fused_training.rs:3384`). (Pearl 2 will stop writing this slot in SP7 T6; T7 replaces the consumer floor with sentinel-aware bootstrap.)", }, RegistryEntry { name: "sp5_budget_iqn", @@ -585,12 +585,12 @@ impl StateResetRegistry { RegistryEntry { name: "sp5_budget_cql", category: ResetCategory::FoldReset, - description: "ISV[BUDGET_CQL_BASE=198..202) — per-branch CQL loss budget share. SP7 (2026-05-03): driven by the loss-balance controller (`loss_balance_controller_kernel`) using flatness-modulated target ratio (CQL/IQN ≤ 2.0×(1−flatness)). Pearl A sentinel 0 at fold boundary; consumer-side bootstrap = CQL_BOOTSTRAP_BUDGET = 0.02 in fused_training.rs::compute_adaptive_budgets.", + description: "ISV[BUDGET_CQL_BASE=198..202) — per-branch CQL loss budget share. SP7 (2026-05-03): will be driven by the loss-balance controller (`loss_balance_controller_kernel`) using flatness-modulated target ratio (CQL/IQN ≤ 2.0×(1−flatness)). Pearl A sentinel 0 at fold boundary; consumer-side floor currently 0.02 (`fused_training.rs:3386`). (Pearl 2 will stop writing this slot in SP7 T6; T7 replaces the consumer floor with sentinel-aware bootstrap.)", }, RegistryEntry { name: "sp5_budget_ens", category: ResetCategory::FoldReset, - description: "ISV[BUDGET_ENS_BASE=202..206) — per-branch ensemble loss budget share. SP7 (2026-05-03): consumer reads with sentinel-aware bootstrap = ENS_BOOTSTRAP_BUDGET = 0.02; Ens is currently not actively driven (no loss-balance target ratio defined for Ens vs IQN). Pearl A sentinel 0 at fold boundary. (Pearl 2 no longer writes this slot post-SP7.)", + description: "ISV[BUDGET_ENS_BASE=202..206) — per-branch ensemble loss budget share. SP7 (2026-05-03): consumer-side floor currently 0.02 (`fused_training.rs:3387`); Ens is currently not actively driven (no loss-balance target ratio defined for Ens vs IQN). Pearl A sentinel 0 at fold boundary. (Pearl 2 will stop writing this slot in SP7 T6; T7 replaces the consumer floor with sentinel-aware bootstrap.)", }, RegistryEntry { name: "sp5_flatness", diff --git a/docs/dqn-wire-up-audit.md b/docs/dqn-wire-up-audit.md index 9709f2550..b48bf138e 100644 --- a/docs/dqn-wire-up-audit.md +++ b/docs/dqn-wire-up-audit.md @@ -3884,6 +3884,7 @@ extended. No producer kernel yet — that arrives in the next commit. - T2 (commit ⟨pending⟩): 4 SP7 ResetEntries + corrected `sp5_budget_cql` description (was claiming a non-existent "regime_stability allocator") + clarified `sp5_budget_c51`/`sp5_budget_ens` to reflect SP7 ownership. + T2 polish landed (commit pending) — registry descriptions corrected to reflect current state vs T6/T7 future changes. - T3: kernel `.cu` file. - T4: build.rs cubin manifest. - T5: trainer struct + launcher fn.