Adds curiosity-driven exploration (ForwardDynamicsModel + ICM reward), configurable branching DQN fields (num_order_types, num_urgency_levels), regime-conditional importance sampling with ADX/CUSUM thresholds, and GPU curiosity training kernel support. Also fixes remaining 5 clippy errors from WIP merge: - gpu_smoketest: add 8 missing DQNConfig fields - curiosity.rs: replace needless_range_loop with slice fill - benchmark files: remove redundant #[cfg_attr] on unconditionally ignored tests 40 files changed, +1486/-1068 lines. 0 clippy errors, 0 warnings. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
196 lines
6.8 KiB
Rust
196 lines
6.8 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,
|
|
)]
|
|
//! Smoke tests for action masking functionality (Wave 9 Agent 2)
|
|
//!
|
|
//! Validates position limit enforcement via action masking.
|
|
//! With branching DQN, the mask has 5 elements (one per exposure level):
|
|
//! [Short100, Short50, Flat, Long50, Long100]
|
|
|
|
use ml::dqn::action_space::{get_valid_action_mask, ExposureLevel, FactoredAction};
|
|
|
|
#[test]
|
|
fn test_action_masking_at_neutral_position() {
|
|
// At position 0.0 with max_position=2.0, all 5 exposure levels valid
|
|
let mask = get_valid_action_mask(0.0, 2.0);
|
|
|
|
assert_eq!(mask.len(), 5, "Mask should have 5 elements (one per exposure level)");
|
|
assert_eq!(
|
|
mask.iter().filter(|&&v| v).count(),
|
|
5,
|
|
"All exposure levels should be valid at position 0.0 with max_position=2.0"
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn test_action_masking_very_restrictive_limit() {
|
|
// With max_position=0.6, only Flat and ±50% exposures should be valid
|
|
let mask = get_valid_action_mask(0.0, 0.6);
|
|
|
|
let valid_count = mask.iter().filter(|&&v| v).count();
|
|
assert_eq!(
|
|
valid_count, 3,
|
|
"Only Flat, Short50, and Long50 should be valid (3/5 exposures)"
|
|
);
|
|
|
|
// Short100 (index 0) invalid: |exposure|=1.0 > 0.6
|
|
assert!(!mask[0], "Short100 should be INVALID (exposure=-1.0 > 0.6)");
|
|
|
|
// Short50 (index 1) valid: |exposure|=0.5 <= 0.6
|
|
assert!(mask[1], "Short50 should be VALID (exposure=-0.5 <= 0.6)");
|
|
|
|
// Flat (index 2) valid: |exposure|=0.0 <= 0.6
|
|
assert!(mask[2], "Flat should be VALID (exposure=0.0 <= 0.6)");
|
|
|
|
// Long50 (index 3) valid: |exposure|=0.5 <= 0.6
|
|
assert!(mask[3], "Long50 should be VALID (exposure=+0.5 <= 0.6)");
|
|
|
|
// Long100 (index 4) invalid: |exposure|=1.0 > 0.6
|
|
assert!(!mask[4], "Long100 should be INVALID (exposure=+1.0 > 0.6)");
|
|
}
|
|
|
|
#[test]
|
|
fn test_action_masking_preserves_all_action_variants() {
|
|
// With masking at max_position=1.0, all 5 exposure levels valid
|
|
let mask = get_valid_action_mask(0.0, 1.0);
|
|
assert_eq!(mask.len(), 5);
|
|
|
|
assert!(mask[0], "Short100 should be valid");
|
|
assert!(mask[1], "Short50 should be valid");
|
|
assert!(mask[2], "Flat should be valid");
|
|
assert!(mask[3], "Long50 should be valid");
|
|
assert!(mask[4], "Long100 should be valid");
|
|
}
|
|
|
|
#[test]
|
|
fn test_action_masking_index_mapping_correctness() {
|
|
let mask = get_valid_action_mask(0.0, 0.6);
|
|
assert_eq!(mask.len(), 5);
|
|
|
|
// Exposure order: Short100, Short50, Flat, Long50, Long100
|
|
assert!(!mask[0], "Short100 (idx 0) should be masked");
|
|
assert!(mask[1], "Short50 (idx 1) should be valid");
|
|
assert!(mask[2], "Flat (idx 2) should be valid");
|
|
assert!(mask[3], "Long50 (idx 3) should be valid");
|
|
assert!(!mask[4], "Long100 (idx 4) should be masked");
|
|
|
|
// Verify FactoredAction mapping still works for the 45-action space
|
|
let action_0 = FactoredAction::from_index(0).unwrap();
|
|
assert_eq!(action_0.exposure, ExposureLevel::Short100);
|
|
|
|
let action_18 = FactoredAction::from_index(18).unwrap();
|
|
assert_eq!(action_18.exposure, ExposureLevel::Flat);
|
|
}
|
|
|
|
#[test]
|
|
fn test_action_masking_boundary_conditions() {
|
|
// At max_position=1.0, all exposure levels valid (max |exp| = 1.0 <= 1.0)
|
|
let mask = get_valid_action_mask(0.0, 1.0);
|
|
let valid_count = mask.iter().filter(|&&v| v).count();
|
|
assert_eq!(valid_count, 5, "All exposures valid when max |exposure| equals max_position");
|
|
|
|
// At max_position=0.99, Short100/Long100 masked (|1.0| > 0.99)
|
|
let mask_below = get_valid_action_mask(0.0, 0.99);
|
|
let valid_below = mask_below.iter().filter(|&&v| v).count();
|
|
assert_eq!(valid_below, 3, "Only 3 exposures valid when max_position < 1.0");
|
|
}
|
|
|
|
#[test]
|
|
fn test_action_masking_flat_always_valid() {
|
|
// Flat (exposure=0.0) should ALWAYS be valid
|
|
for max_pos in &[0.1, 0.5, 1.0, 2.0, 10.0] {
|
|
let mask = get_valid_action_mask(0.0, *max_pos);
|
|
assert!(
|
|
mask[2], // Flat is index 2 in the 5-element mask
|
|
"Flat should always be valid (max_position={})",
|
|
max_pos
|
|
);
|
|
}
|
|
}
|
|
|
|
#[test]
|
|
fn test_action_masking_edge_case_zero_max_position() {
|
|
// max_position=0.0 should only allow Flat (|0.0| <= 0.0)
|
|
let mask = get_valid_action_mask(0.0, 0.0);
|
|
|
|
let valid_count = mask.iter().filter(|&&v| v).count();
|
|
assert_eq!(valid_count, 1, "Only Flat should be valid when max_position=0.0");
|
|
|
|
assert!(!mask[0], "Short100 invalid at max_position=0.0");
|
|
assert!(!mask[1], "Short50 invalid at max_position=0.0");
|
|
assert!(mask[2], "Flat valid at max_position=0.0");
|
|
assert!(!mask[3], "Long50 invalid at max_position=0.0");
|
|
assert!(!mask[4], "Long100 invalid at max_position=0.0");
|
|
}
|