foxhunt/ml/tests/dqn_hyperopt_edge_cases.rs

//! DQN-Specific Edge Case Tests for Hyperparameter Optimization
//!
//! This test suite covers DQN-specific edge cases:
//! 1. Replay buffer size constraints
//! 2. Epsilon decay edge cases
//! 3. Gamma (discount factor) boundaries
//! 4. Batch size vs buffer size constraints
//!
//! Purpose: Ensure DQN adapter handles RL-specific edge cases robustly

use ml::hyperopt::adapters::dqn::{DQNParams, DQNTrainer};
use ml::hyperopt::traits::{HyperparameterOptimizable, ParameterSpace};

// ============================================================================
// REPLAY BUFFER CONSTRAINTS
// ============================================================================

#[test]
fn test_buffer_size_min_bound() {
    let mut params = DQNParams::default();
    params.buffer_size = 10_000; // Minimum bound

    let continuous = params.to_continuous();
    let recovered =
        DQNParams::from_continuous(&continuous).expect("Min buffer size should be valid");

    assert_eq!(recovered.buffer_size, 10_000);
}

#[test]
fn test_buffer_size_max_bound() {
    let mut params = DQNParams::default();
    params.buffer_size = 1_000_000; // Maximum bound

    let continuous = params.to_continuous();
    let recovered =
        DQNParams::from_continuous(&continuous).expect("Max buffer size should be valid");

    assert_eq!(recovered.buffer_size, 1_000_000);
}

#[test]
fn test_batch_size_vs_buffer_size() {
    // Batch size should be <= buffer size
    let params = DQNParams {
        learning_rate: 1e-4,
        batch_size: 128,
        gamma: 0.99,
        epsilon_decay: 0.995,
        buffer_size: 100_000,
    };

    assert!(
        params.batch_size <= params.buffer_size,
        "Batch size {} should be <= buffer size {}",
        params.batch_size,
        params.buffer_size
    );
}

// ============================================================================
// EPSILON DECAY EDGE CASES
// ============================================================================

#[test]
fn test_epsilon_decay_bounds() {
    let bounds = DQNParams::continuous_bounds();

    // Epsilon decay bounds: [ln(0.990), ln(0.999)]
    let min_decay = bounds[3].0.exp();
    let max_decay = bounds[3].1.exp();

    assert!((min_decay - 0.990).abs() < 1e-6);
    assert!((max_decay - 0.999).abs() < 1e-6);
}

#[test]
fn test_epsilon_decay_min() {
    let mut params = DQNParams::default();
    params.epsilon_decay = 0.990; // Fast decay

    let continuous = params.to_continuous();
    let recovered =
        DQNParams::from_continuous(&continuous).expect("Min epsilon decay should be valid");

    assert!((recovered.epsilon_decay - 0.990).abs() < 1e-6);
}

#[test]
fn test_epsilon_decay_max() {
    let mut params = DQNParams::default();
    params.epsilon_decay = 0.999; // Slow decay

    let continuous = params.to_continuous();
    let recovered =
        DQNParams::from_continuous(&continuous).expect("Max epsilon decay should be valid");

    assert!((recovered.epsilon_decay - 0.999).abs() < 1e-6);
}

// ============================================================================
// GAMMA (DISCOUNT FACTOR) BOUNDARIES
// ============================================================================

#[test]
fn test_gamma_bounds() {
    let bounds = DQNParams::continuous_bounds();

    // Gamma bounds: [0.95, 0.99]
    assert_eq!(bounds[2], (0.95, 0.99));
}

#[test]
fn test_gamma_min() {
    let mut params = DQNParams::default();
    params.gamma = 0.95; // Short-term focused

    let continuous = params.to_continuous();
    let recovered = DQNParams::from_continuous(&continuous).expect("Min gamma should be valid");

    assert!((recovered.gamma - 0.95).abs() < 1e-10);
}

#[test]
fn test_gamma_max() {
    let mut params = DQNParams::default();
    params.gamma = 0.99; // Long-term focused

    let continuous = params.to_continuous();
    let recovered = DQNParams::from_continuous(&continuous).expect("Max gamma should be valid");

    assert!((recovered.gamma - 0.99).abs() < 1e-10);
}

// ============================================================================
// BATCH SIZE CONSTRAINTS
// ============================================================================

#[test]
fn test_batch_size_min_bound() {
    let bounds = DQNParams::continuous_bounds();

    // Batch size bounds: [32, 230]
    assert_eq!(bounds[1], (32.0, 230.0));
}

#[test]
fn test_batch_size_rtx_3050_ti_constraint() {
    // RTX 3050 Ti max batch size = 230
    let mut params = DQNParams::default();
    params.batch_size = 230; // Maximum for RTX 3050 Ti

    let continuous = params.to_continuous();
    let recovered =
        DQNParams::from_continuous(&continuous).expect("Max batch size should be valid");

    assert_eq!(recovered.batch_size, 230);
}

#[test]
fn test_batch_size_clamping() {
    // Test that batch sizes outside [32, 230] are clamped
    let too_small = vec![
        (-4.0_f64).ln(),    // learning_rate
        10.0,               // batch_size (below min)
        0.99,               // gamma
        (0.995_f64).ln(),   // epsilon_decay
        (100_000_f64).ln(), // buffer_size
    ];

    let params_small = DQNParams::from_continuous(&too_small).expect("Should clamp batch size");
    assert!(params_small.batch_size >= 32, "Should clamp to min");

    let too_large = vec![
        (-4.0_f64).ln(),    // learning_rate
        1000.0,             // batch_size (above max)
        0.99,               // gamma
        (0.995_f64).ln(),   // epsilon_decay
        (100_000_f64).ln(), // buffer_size
    ];

    let params_large = DQNParams::from_continuous(&too_large).expect("Should clamp batch size");
    assert!(params_large.batch_size <= 230, "Should clamp to max");
}

// ============================================================================
// PARAMETER ROUNDTRIP TESTS
// ============================================================================

#[test]
fn test_dqn_params_roundtrip() {
    let params = DQNParams {
        learning_rate: 1e-4,
        batch_size: 128,
        gamma: 0.99,
        epsilon_decay: 0.995,
        buffer_size: 100_000,
    };

    let continuous = params.to_continuous();
    let recovered = DQNParams::from_continuous(&continuous).expect("Roundtrip should succeed");

    assert!((recovered.learning_rate - params.learning_rate).abs() < 1e-10);
    assert_eq!(recovered.batch_size, params.batch_size);
    assert!((recovered.gamma - params.gamma).abs() < 1e-10);
    assert!((recovered.epsilon_decay - params.epsilon_decay).abs() < 1e-6);
    assert_eq!(recovered.buffer_size, params.buffer_size);
}

#[test]
fn test_extreme_values_roundtrip() {
    // Test boundary values
    let extreme_params = DQNParams {
        learning_rate: 1e-5,
        batch_size: 32,
        gamma: 0.95,
        epsilon_decay: 0.990,
        buffer_size: 10_000,
    };

    let continuous = extreme_params.to_continuous();
    let recovered =
        DQNParams::from_continuous(&continuous).expect("Extreme values should roundtrip");

    assert!((recovered.learning_rate - extreme_params.learning_rate).abs() < 1e-10);
    assert_eq!(recovered.batch_size, extreme_params.batch_size);
    assert!((recovered.gamma - extreme_params.gamma).abs() < 1e-10);
}

// ============================================================================
// PARAMETER NAMES
// ============================================================================

#[test]
fn test_param_names() {
    let names = DQNParams::param_names();

    assert_eq!(names.len(), 5);
    assert_eq!(names[0], "learning_rate");
    assert_eq!(names[1], "batch_size");
    assert_eq!(names[2], "gamma");
    assert_eq!(names[3], "epsilon_decay");
    assert_eq!(names[4], "buffer_size");
}

// ============================================================================
// TRAINER CREATION
// ============================================================================

#[test]
fn test_dqn_trainer_invalid_path() {
    let result = DQNTrainer::new("nonexistent_directory", 100);

    assert!(result.is_err(), "Should error on nonexistent directory");

    let err_msg = format!("{:?}", result.unwrap_err());
    assert!(
        err_msg.contains("not found") || err_msg.contains("Config"),
        "Should mention directory not found"
    );
}

// ============================================================================
// INTEGRATION TESTS
// ============================================================================

#[test]
fn test_default_params_valid() {
    let params = DQNParams::default();

    // Verify default values are reasonable
    assert!(params.learning_rate > 0.0);
    assert!(params.batch_size > 0);
    assert!(params.gamma > 0.0 && params.gamma <= 1.0);
    assert!(params.epsilon_decay > 0.0 && params.epsilon_decay <= 1.0);
    assert!(params.buffer_size > 0);
    assert!(params.batch_size <= params.buffer_size);
}

#[test]
fn test_parameter_space_coverage() {
    let bounds = DQNParams::continuous_bounds();

    // Sample midpoint of parameter space
    let midpoint: Vec<f64> = bounds.iter().map(|(min, max)| (min + max) / 2.0).collect();

    let params = DQNParams::from_continuous(&midpoint).expect("Midpoint should be valid");

    // Verify all params are in valid ranges
    assert!(params.learning_rate > 0.0);
    assert!(params.batch_size >= 32 && params.batch_size <= 230);
    assert!(params.gamma >= 0.95 && params.gamma <= 0.99);
    assert!(params.epsilon_decay >= 0.990 && params.epsilon_decay <= 0.999);
    assert!(params.buffer_size >= 10_000 && params.buffer_size <= 1_000_000);
}

#[test]
fn test_learning_rate_log_scale() {
    // Verify learning rate uses log scale
    let params1 = DQNParams {
        learning_rate: 1e-5,
        ..Default::default()
    };

    let params2 = DQNParams {
        learning_rate: 1e-3,
        ..Default::default()
    };

    let cont1 = params1.to_continuous();
    let cont2 = params2.to_continuous();

    // Log scale: ln(1e-5) vs ln(1e-3)
    assert!(cont1[0] < cont2[0]);

    // Difference should be log(100) ≈ 4.6
    let log_diff = (cont2[0] - cont1[0]).abs();
    assert!((log_diff - (100.0_f64).ln()).abs() < 0.1);
}