diff --git a/crates/ml/tests/smoke_test_real_data.rs b/crates/ml/tests/smoke_test_real_data.rs index a63004b04..a04af75ec 100644 --- a/crates/ml/tests/smoke_test_real_data.rs +++ b/crates/ml/tests/smoke_test_real_data.rs @@ -709,7 +709,11 @@ mod gpu_smoke { episode_length: timesteps, epsilon: 0.0, // NoisyNets handle exploration gamma: 0.99, - noisy_sigma_init: 0.5, + // sigma must be large enough that NoisyNet noise dominates Q-value gaps + // even on wide networks (256-dim). With random Xavier init on a 256-wide + // network, Q-values are O(1/sqrt(256)) ≈ 0.06 apart. sigma=2.0 ensures + // noise O(sigma/sqrt(fan_in)) ≈ 0.12 exceeds this gap. + noisy_sigma_init: 2.0, num_atoms: 51, v_min: -10.0, v_max: 10.0,