Files
foxhunt/crates/ml/tests/dqn_hyperparams_kelly_fields_test.rs
jgrusewski d64adc14f5 refactor(dqn): f64 → f32 for kernel-facing hyperparams
Eliminates the f64→f32 cudarc ABI trap (feedback_cudarc_f64_f32_abi.md,
task #82) at the type level: hyperparameters consumed by CUDA kernels
now live as f32 in Rust, cast once at the TOML/PSO ingest boundary
instead of at every kernel call site.

Structs changed:
  - DQNHyperparameters (crates/ml/src/trainers/dqn/config.rs) —
    ~85 scalar fields migrated from f64 → f32. Covers all
    kernel-facing scalars: reward weights (w_pnl/w_dd/w_idle,
    dd_threshold, cea_weight, micro_reward_*, price_confirm_weight,
    book_aggression_weight, hold_quality_weight), exploration
    (epsilon_* and the 4 branch mults, noisy_sigma_*, count_bonus,
    noise_sigma, q_gap_threshold), distributional RL (v_min, v_max,
    reward_scale, iqn_lambda, qr_kappa, spectral_*,
    gradient_collapse_multiplier), fill simulation (5 fill_*
    fields), risk/Kelly (kelly_fractional, kelly_max_fraction,
    max_leverage, max_position_absolute, minimum_profit_factor),
    ensemble/curiosity (curiosity_weight,
    curiosity_q_penalty_lambda, ensemble_*, beta_*, variance_cap),
    anti-LR (anti_lr_*, adversarial_dd_threshold,
    beta_penalty_strength), walk-forward (wf_*),
    experience (avg_spread, transaction_cost_multiplier,
    holding_cost_rate, churn_penalty_scale, contract_multiplier,
    margin_pct, tick_size, bars_per_day, cash_reserve_percent),
    misc kernel scalars (gamma, tau, huber_delta, q_clip_*,
    shrink_perturb_*, regime_replay_decay, per_alpha,
    per_beta_start, dt_target_return, etc.). Also
    `noisy_epsilon_floor: Option<f32>` and
    `count_bonus_coefficient: Option<f32>`.
  - `computed_v_min` / `computed_v_max` now return f32.
  - `compute_max_position` returns f32 (f64 internally for the
    notional division).

Fields preserved as f64 (precision-sensitive, NOT kernel-facing
scalars — per task spec and feedback_cudarc_f64_f32_abi.md):
  - `learning_rate` — tested at 1e-10 tolerance; f32 rounds to
    2e-12 for a 1e-5 LR.
  - `entropy_coefficient` — tested at 1e-9 tolerance.
  - `weight_decay` — tiny 1e-5..1e-3 range.
  - `adam_epsilon` — 1e-8 default; f32 preserves denorms here but
    paired with weight_decay/learning_rate for symmetry.
  - `gradient_clip_norm: Option<f64>` — grad norms are f64
    accumulators by project convention.
  - `min_loss_improvement_pct`, `q_value_floor` — early-stopping
    long-horizon stats.
  - `cql_alpha` — flows into DQNConfig (ml-dqn) still f64.
  - `min_learning_rate`, `lr_min` — paired with learning_rate.
  - Family intensity scalars (6 `*_intensity` fields) — f64 PSO
    search space; the intensity applies via `as f32` at each call
    site in `apply_family_scaling`.

No checkpoint format change: DQNHyperparameters has
`#[derive(Debug, Clone)]` only (not Serialize/Deserialize), so the
TOML-ingest path is the only serde boundary and already casts
explicitly via `hp.field = v as f32;` in
`DqnTrainingProfile::apply_to`. PSO hyperopt bounds stay f64 in
`SearchSpaceSection` and cast at the adapter boundary.

Call-site impact:
  - ~30 `as f32` casts removed from hot paths (fused_training
    FusedConfig builder, training_loop kernel launches,
    constructor DQNConfig builder, action.rs GPU action selector,
    trainer/mod.rs WF config). Kernels now receive the hp field
    directly via `&hp.x`.
  - ~75 `as f32` casts added at the `apply_to` / hyperopt-adapter
    ingest boundary — the single conversion point.
  - Cross-crate contracts (DQNConfig in ml-dqn, PortfolioTracker
    in ml-core, GAECalculator, DropoutScheduler, NoisySigmaScheduler,
    KellyOptimizerConfig, RewardConfig) retain their f64 signatures;
    ml calls cast at the boundary with `f64::from(hp.x)` so the
    contract is explicit and greppable.

Two test-side adjustments:
  - `test_kelly_fields_are_public` now asserts `f32` for
    kelly_fractional / kelly_max_fraction (these migrated).
  - `test_early_stopping_termination` uses `f64::from(...)` to
    preserve the f64 threshold computation against the now-f32
    `gradient_collapse_multiplier`.

Verified:
  - `SQLX_OFFLINE=true CARGO_INCREMENTAL=0 RUSTC_WRAPPER=sccache
    cargo check --workspace` — clean, zero new warnings.
  - `cargo check --workspace --tests` — clean.
  - `cargo test -p ml --lib training_profile::tests` — all 18
    migrated tests pass. The one pre-existing failure
    (`test_production_profile_applies_all_sections` n_steps
    mismatch, 1 vs 5) reproduces on stashed baseline, so it is
    unrelated to this change.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-24 01:55:14 +02:00

196 lines
6.9 KiB
Rust

#![allow(
clippy::assertions_on_constants,
clippy::assertions_on_result_states,
clippy::clone_on_copy,
clippy::decimal_literal_representation,
clippy::doc_markdown,
clippy::empty_line_after_doc_comments,
clippy::field_reassign_with_default,
clippy::get_unwrap,
clippy::identity_op,
clippy::inconsistent_digit_grouping,
clippy::indexing_slicing,
clippy::integer_division,
clippy::len_zero,
clippy::let_underscore_must_use,
clippy::manual_div_ceil,
clippy::manual_let_else,
clippy::manual_range_contains,
clippy::modulo_arithmetic,
clippy::needless_range_loop,
clippy::non_ascii_literal,
clippy::redundant_clone,
clippy::shadow_reuse,
clippy::shadow_same,
clippy::shadow_unrelated,
clippy::single_match_else,
clippy::str_to_string,
clippy::string_slice,
clippy::tests_outside_test_module,
clippy::too_many_lines,
clippy::unnecessary_wraps,
clippy::unseparated_literal_suffix,
clippy::use_debug,
clippy::useless_vec,
clippy::wildcard_enum_match_arm,
clippy::else_if_without_else,
clippy::expect_used,
clippy::missing_const_for_fn,
clippy::similar_names,
clippy::type_complexity,
clippy::collapsible_else_if,
clippy::doc_lazy_continuation,
clippy::items_after_test_module,
clippy::map_clone,
clippy::multiple_unsafe_ops_per_block,
clippy::unwrap_or_default,
clippy::assign_op_pattern,
clippy::needless_borrow,
clippy::println_empty_string,
clippy::unnecessary_cast,
clippy::used_underscore_binding,
clippy::create_dir,
clippy::implicit_saturating_sub,
clippy::exit,
clippy::expect_fun_call,
clippy::too_many_arguments,
clippy::unnecessary_map_or,
clippy::unwrap_used,
dead_code,
unused_imports,
unused_variables,
clippy::cloned_ref_to_slice_refs,
clippy::neg_multiply,
clippy::while_let_loop,
clippy::bool_assert_comparison,
clippy::excessive_precision,
clippy::trivially_copy_pass_by_ref,
clippy::op_ref,
clippy::redundant_closure,
clippy::unnecessary_lazy_evaluations,
clippy::if_then_some_else_none,
clippy::unnecessary_to_owned,
clippy::single_component_path_imports,
)]
//! Test Suite: DQN Hyperparameters Kelly Fields Validation
//!
//! Purpose: Verify that DQNHyperparameters struct has all 4 Kelly sizing fields
//! and that they are correctly configured with sensible defaults.
//!
//! This test validates WAVE 19 Agent 2's requirement that Kelly parameters
//! are properly integrated into the hyperparameters struct.
#[cfg(test)]
mod dqn_hyperparams_kelly_tests {
use ml::trainers::dqn::DQNHyperparameters;
#[test]
fn test_hyperparams_has_kelly_fractional() {
let hyperparams = DQNHyperparameters::conservative();
// Should compile if field exists
let _kelly = hyperparams.kelly_fractional;
// Verify it's accessible
assert!(hyperparams.kelly_fractional > 0.0);
}
#[test]
fn test_hyperparams_has_kelly_max_fraction() {
let hyperparams = DQNHyperparameters::conservative();
let _kelly_max = hyperparams.kelly_max_fraction;
// Verify it's accessible
assert!(hyperparams.kelly_max_fraction > 0.0);
}
#[test]
fn test_hyperparams_has_kelly_min_trades() {
let hyperparams = DQNHyperparameters::conservative();
let _min_trades = hyperparams.kelly_min_trades;
// Verify it's accessible
assert!(hyperparams.kelly_min_trades > 0);
}
#[test]
fn test_hyperparams_has_volatility_window() {
let hyperparams = DQNHyperparameters::conservative();
let _vol_window = hyperparams.volatility_window;
// Verify it's accessible
assert!(hyperparams.volatility_window > 0);
}
#[test]
fn test_custom_kelly_params_can_be_set() {
let mut hyperparams = DQNHyperparameters::conservative();
// Set custom values
hyperparams.kelly_fractional = 0.75;
hyperparams.kelly_max_fraction = 0.4;
hyperparams.kelly_min_trades = 35;
hyperparams.volatility_window = 25;
// Verify they were set correctly
assert_eq!(hyperparams.kelly_fractional, 0.75);
assert_eq!(hyperparams.kelly_max_fraction, 0.4);
assert_eq!(hyperparams.kelly_min_trades, 35);
assert_eq!(hyperparams.volatility_window, 25);
}
#[test]
fn test_default_kelly_params_are_reasonable() {
let hyperparams = DQNHyperparameters::conservative();
// Check defaults are within hyperopt bounds (from Agent 1 specification)
// kelly_fractional: [0.25, 1.0]
assert!(hyperparams.kelly_fractional >= 0.25 && hyperparams.kelly_fractional <= 1.0,
"Default kelly_fractional ({}) should be in [0.25, 1.0]", hyperparams.kelly_fractional);
// kelly_max_fraction: [0.1, 0.5]
assert!(hyperparams.kelly_max_fraction >= 0.1 && hyperparams.kelly_max_fraction <= 0.5,
"Default kelly_max_fraction ({}) should be in [0.1, 0.5]", hyperparams.kelly_max_fraction);
// kelly_min_trades: [10, 50]
assert!(hyperparams.kelly_min_trades >= 10 && hyperparams.kelly_min_trades <= 50,
"Default kelly_min_trades ({}) should be in [10, 50]", hyperparams.kelly_min_trades);
// volatility_window: [10, 30]
assert!(hyperparams.volatility_window >= 10 && hyperparams.volatility_window <= 30,
"Default volatility_window ({}) should be in [10, 30]", hyperparams.volatility_window);
}
#[test]
fn test_kelly_fields_are_public() {
// This test verifies that all Kelly fields are pub (accessible to hyperopt adapter)
let hyperparams = DQNHyperparameters::conservative();
// If these compile, the fields are public.
// Post f64→f32 migration: risk/kelly scalars now f32 (kernel-facing).
let _: f32 = hyperparams.kelly_fractional;
let _: f32 = hyperparams.kelly_max_fraction;
let _: usize = hyperparams.kelly_min_trades;
let _: usize = hyperparams.volatility_window;
}
#[test]
fn test_expected_default_values() {
let hyperparams = DQNHyperparameters::conservative();
// From trainer code (lines 629-632):
// kelly_fractional: 0.5 (half-Kelly, conservative)
// kelly_max_fraction: 0.25 (max 25% of portfolio)
// kelly_min_trades: 20 (20 trades minimum)
// volatility_window: 20 (20-period rolling window)
assert_eq!(hyperparams.kelly_fractional, 0.5,
"Expected default kelly_fractional=0.5 (half-Kelly)");
assert_eq!(hyperparams.kelly_max_fraction, 0.25,
"Expected default kelly_max_fraction=0.25 (25% max)");
assert_eq!(hyperparams.kelly_min_trades, 20,
"Expected default kelly_min_trades=20");
assert_eq!(hyperparams.volatility_window, 20,
"Expected default volatility_window=20");
}
}