diff --git a/crates/ml/src/ppo/ppo.rs b/crates/ml/src/ppo/ppo.rs index 7edb65027..a12fd917d 100644 --- a/crates/ml/src/ppo/ppo.rs +++ b/crates/ml/src/ppo/ppo.rs @@ -275,7 +275,7 @@ impl Default for PPOConfig { lstm_num_layers: 1, lstm_sequence_length: 32, accumulation_steps: 1, - clip_epsilon_high: None, + clip_epsilon_high: Some(0.28), // DAPO asymmetric clipping: [1-0.2, 1+0.28] = [0.8, 1.28] mixed_precision: None, } }