feat(ppo): enable DAPO asymmetric clipping by default (clip_epsilon_high=0.28)

Clip range [1-0.2, 1+0.28] = [0.8, 1.28] allows larger policy updates
toward profitable actions while being conservative about penalizing
exploration. ByteDance DAPO 2025 — 50% faster convergence.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

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,
         }
     }