diff --git a/crates/ml/src/hyperopt/adapters/dqn.rs b/crates/ml/src/hyperopt/adapters/dqn.rs index fe7b9ee58..690a1dab1 100644 --- a/crates/ml/src/hyperopt/adapters/dqn.rs +++ b/crates/ml/src/hyperopt/adapters/dqn.rs @@ -517,8 +517,8 @@ impl ParameterSpace for DQNParams { // CQL regularization (1D) (0.0, 0.5), // 25: cql_alpha (linear, 0.0=disabled, 0.1=mild, 0.5=moderate) - // Eval softmax temperature (1D) - (0.01_f64.ln(), 2.0_f64.ln()), // 26: eval_softmax_temp (log scale) + // Eval softmax temperature (1D) — floor at 0.1 prevents near-greedy collapse + (0.1_f64.ln(), 2.0_f64.ln()), // 26: eval_softmax_temp (log scale) ] } @@ -3552,7 +3552,7 @@ mod tests { 256.0, // hidden_dim_base min 0.02, // noisy_epsilon_floor min 0.0, // cql_alpha min - 0.01_f64.ln(), // eval_softmax_temp min + 0.1_f64.ln(), // eval_softmax_temp min ]; let params_min = DQNParams::from_continuous(&continuous_min).unwrap(); assert!((params_min.per_alpha - 0.4).abs() < 1e-6);