fix: keep async rollouts version-consistent

- serialize shared-model optimizer updates with generation
- reject future or over-lagged rollout results after asynchronous scoring
- close cache publication races
- persist policy versions in online checkpoints
This commit is contained in:
0z5a
2026-09-03 12:01:24 +08:00
parent ce2f9d13b3
commit 587b0ee046
16 changed files with 531 additions and 49 deletions
+1
View File
@@ -156,6 +156,7 @@ provide a command-line option for configuring one.
| Parameter | Description | Default |
|-----------|-------------|---------|
| `--rollout_interval` | Optimizer steps between rollout refreshes | 512 |
| `--rollout_max_policy_lag` | Maximum accepted rollout/live policy-version gap (`None` derives `rollout_interval - 1`) | None |
| `--rollout_temperature` | Rollout sampling temperature | 0.7 |
| `--rollout_top_k` | Rollout top-k filtering (`0` disables) | 0 |
| `--rollout_top_p` | Rollout nucleus sampling threshold | 0.9 |