gitadmin/foxhunt
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(bf16): 1722/1722 tests pass — ALL PASS, zero failures

Browse Source 
Fix last 2 tests:
- action_masking: test used 81-action FactoredAction decoder for
  45-action mask. Fixed to use mask's own 5×9 exposure encoding.
- hyperopt bounds: test both Full (all ranges) and Fast (architecture
  fixed) phases. Implemented phase_fast override in continuous_bounds
  to pin hidden_dim_base, num_atoms, dueling_hidden_dim from TOML.

Final scorecard:
  ml-core:   300/300  (100%)
  ml-dqn:    359/359  (100%)
  ml-ppo:    168/168  (100%)
  ml:        895/895  (100%)
  Total:    1722/1722 (100%)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
jgrusewski
2026-03-28 13:11:47 +01:00
parent 3738677d46
commit 9b02f86fca
3 changed files with 69 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

69
crates/ml-ppo/src/action_masking.rs
View File

@@ -210,50 +210,51 @@ mod tests {
#[test]
fn test_45_action_masking_canonical_layout() {
use ml_core::action_space::{ExposureLevel, FactoredAction};
// 45-action layout: 5 exposure levels × 9 sub-actions each
// exposure_idx = action_idx / 9:
// 0 = Short100, 1 = Short50, 2 = Flat, 3 = Long50, 4 = Long100
let max_position = 5.0;
// At max position: Long50 (idx 3) and Long100 (idx 4) should be masked
let mask = create_action_mask(max_position, max_position, 45);
for idx in 0..45 {
if let Ok(action) = FactoredAction::from_index(idx) {
match action.exposure {
ExposureLevel::Long50 | ExposureLevel::Long100 => {
assert!(
!mask.get(idx).copied().unwrap_or(true),
"Long action {} should be masked at max position",
idx
);
}
_ => {
assert!(
mask.get(idx).copied().unwrap_or(false),
"Non-long action {} should NOT be masked at max position",
idx
);
}
let exposure_idx = idx / 9;
match exposure_idx {
3 | 4 => {
assert!(
!mask[idx],
"Long action {} (exposure_idx={}) should be masked at max position",
idx, exposure_idx
);
}
_ => {
assert!(
mask[idx],
"Non-long action {} (exposure_idx={}) should NOT be masked at max position",
idx, exposure_idx
);
}
}
}
// At min position: Short100 (idx 0) and Short50 (idx 1) should be masked
let mask = create_action_mask(-max_position, max_position, 45);
for idx in 0..45 {
if let Ok(action) = FactoredAction::from_index(idx) {
match action.exposure {
ExposureLevel::Short50 | ExposureLevel::Short100 => {
assert!(
!mask.get(idx).copied().unwrap_or(true),
"Short action {} should be masked at min position",
idx
);
}
_ => {
assert!(
mask.get(idx).copied().unwrap_or(false),
"Non-short action {} should NOT be masked at min position",
idx
);
}
let exposure_idx = idx / 9;
match exposure_idx {
0 | 1 => {
assert!(
!mask[idx],
"Short action {} (exposure_idx={}) should be masked at min position",
idx, exposure_idx
);
}
_ => {
assert!(
mask[idx],
"Non-short action {} (exposure_idx={}) should NOT be masked at min position",
idx, exposure_idx
);
}
}
}

33
crates/ml/src/hyperopt/adapters/dqn.rs
View File

@@ -531,7 +531,7 @@ impl ParameterSpace for DQNParams {
let cw = b("c51_warmup_epochs", (3.0, 15.0));
let iq = b("iqn_lambda", (0.0, 1.0));
let bounds = vec![
let mut bounds = vec![
(lr.0.ln(), lr.1.ln()), // 0: learning_rate (log scale)
bs, // 1: batch_size
gm, // 2: gamma
@@ -556,6 +556,20 @@ impl ParameterSpace for DQNParams {
iq, // 21: iqn_lambda
];
// Phase Fast: fix architecture dims to single-point bounds
if crate::training_profile::get_hyperopt_phase() == crate::training_profile::HyperoptPhase::Fast {
if let Some(pf) = &hp.phase_fast {
let fix = |bounds: &mut Vec<(f64, f64)>, idx: usize, val: Option<f64>| {
if let Some(v) = val {
bounds[idx] = (v, v);
}
};
fix(&mut bounds, 10, pf.dueling_hidden_dim); // dueling_hidden_dim
fix(&mut bounds, 13, pf.num_atoms); // num_atoms
fix(&mut bounds, 18, pf.hidden_dim_base); // hidden_dim_base
}
}
bounds
}
@@ -3619,6 +3633,10 @@ mod tests {
#[test]
fn test_dqn_params_bounds() {
use crate::training_profile::{set_hyperopt_phase, HyperoptPhase};
// Test Full phase: all bounds must be ranges (lower < upper)
set_hyperopt_phase(HyperoptPhase::Full(vec![0.0; 22]));
let bounds = DQNParams::continuous_bounds();
assert_eq!(bounds.len(), 22); // 22D consolidated search space
@@ -3637,11 +3655,18 @@ mod tests {
assert!(lr_min > 0.0 && lr_min < 1e-3, "Learning rate lower bound should be small, got {:.2e}", lr_min);
assert!(lr_max >= 1e-4 && lr_max <= 1e-2, "Learning rate upper bound should be reasonable, got {:.2e}", lr_max);
// Check all bounds have valid ranges (lower < upper)
// Exact values may be overridden by HyperoptProfile YAML
for (i, (lo, hi)) in bounds.iter().enumerate() {
assert!(lo < hi, "Bound {i}: lower ({lo}) must be < upper ({hi})");
assert!(lo < hi, "Full phase: Bound {i}: lower ({lo}) must be < upper ({hi})");
}
// Test Fast phase: architecture dims must be fixed (single-point bounds)
set_hyperopt_phase(HyperoptPhase::Fast);
let fast_bounds = DQNParams::continuous_bounds();
assert_eq!(fast_bounds[18].0, fast_bounds[18].1, "Fast: hidden_dim_base must be fixed");
assert_eq!(fast_bounds[13].0, fast_bounds[13].1, "Fast: num_atoms must be fixed");
assert_eq!(fast_bounds[10].0, fast_bounds[10].1, "Fast: dueling_hidden_dim must be fixed");
// Learning rate must still be a range in Fast phase
assert_ne!(fast_bounds[0].0, fast_bounds[0].1, "Fast: learning_rate must still be searchable");
}
#[test]

12
crates/ml/src/training_profile.rs
View File

@@ -1014,13 +1014,11 @@ mod tests {
set_hyperopt_phase(HyperoptPhase::Fast);
use crate::hyperopt::ParameterSpace;
let bounds = crate::hyperopt::adapters::dqn::DQNParams::continuous_bounds();
// Index 21: hidden_dim_base, 15: num_atoms, 28: branch_hidden_dim,
// 13: dueling_hidden_dim, 10: v_range
assert_eq!(bounds[21].0, bounds[21].1, "hidden_dim_base must be fixed");
assert_eq!(bounds[15].0, bounds[15].1, "num_atoms must be fixed");
assert_eq!(bounds[28].0, bounds[28].1, "branch_hidden_dim must be fixed");
assert_eq!(bounds[13].0, bounds[13].1, "dueling_hidden_dim must be fixed");
assert_eq!(bounds[10].0, bounds[10].1, "v_range must be fixed");
// 22D search space indices (from DQNParams::continuous_bounds):
// 10: dueling_hidden_dim, 13: num_atoms, 18: hidden_dim_base
assert_eq!(bounds[18].0, bounds[18].1, "hidden_dim_base must be fixed");
assert_eq!(bounds[13].0, bounds[13].1, "num_atoms must be fixed");
assert_eq!(bounds[10].0, bounds[10].1, "dueling_hidden_dim must be fixed");
// Learning rate (index 0) must still be a range.
assert_ne!(bounds[0].0, bounds[0].1, "learning_rate must still be searchable");
}