fix(gpu-per): clamp priorities after index_add to prevent NaN weights

index_add with duplicate indices double-applies deltas — e.g. if index i
is sampled twice with delta -0.5, priority goes 1.0 + (-0.5) + (-0.5) = 0.0,
causing NaN in importance sampling weights. Post-clamp to [epsilon, 1e6]
ensures priorities stay positive.

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

crates/ml-dqn/src/gpu_replay_buffer.rs

@@ -595,13 +595,15 @@ impl GpuReplayBuffer {
         // then index_add the deltas back. Single batched GPU kernel, no CPU loop.
         //
         // For rare duplicate indices (batch_size << capacity), the deltas may
-        // stack incorrectly, but this is benign: priorities will be slightly off
-        // and self-correct on the next update. This matches the old CPU loop's
-        // "last-write-wins" semantics in expectation.
+        // stack — index_add adds ALL deltas, so duplicates double-apply.
+        // Post-clamp prevents priorities from going to zero/negative (→ NaN weights).
         let indices_i64 = indices.to_dtype(DType::I64)?;
         let old_prios = self.priorities.index_select(&indices_i64, 0)?;
         let delta = (&clamped - &old_prios)?;
-        self.priorities = self.priorities.index_add(&indices_i64, &delta, 0)?;
+        self.priorities = self
+            .priorities
+            .index_add(&indices_i64, &delta, 0)?
+            .clamp(self.config.epsilon, 1e6)?;
 
         Ok(())
     }