Sync policy_update720.state.json (af5322dbe8ae)
Browse files
ppo_v86/policy_update720.state.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"checkpoint_schema_version": 2,
|
| 3 |
+
"hidden_reset_policy": "episode_done",
|
| 4 |
+
"update": 721,
|
| 5 |
+
"stage": 6,
|
| 6 |
+
"ent_scale": 1.4670207469681316,
|
| 7 |
+
"lr_now": 0.00009428737890624998,
|
| 8 |
+
"total_env_steps": 1887232,
|
| 9 |
+
"recent_wins": [
|
| 10 |
+
0.0,
|
| 11 |
+
0.0,
|
| 12 |
+
0.0,
|
| 13 |
+
0.0,
|
| 14 |
+
0.0,
|
| 15 |
+
0.0,
|
| 16 |
+
0.0,
|
| 17 |
+
0.0,
|
| 18 |
+
0.0,
|
| 19 |
+
0.0,
|
| 20 |
+
1.0,
|
| 21 |
+
0.0
|
| 22 |
+
],
|
| 23 |
+
"recent_conversions": [
|
| 24 |
+
1.0
|
| 25 |
+
],
|
| 26 |
+
"best_eval_win": null,
|
| 27 |
+
"best_eval_score": null,
|
| 28 |
+
"v81_curriculum": true,
|
| 29 |
+
"curriculum_schedule": "v8.3",
|
| 30 |
+
"reward_profile": "v8.6-attack-fair-v1",
|
| 31 |
+
"return_stats": null,
|
| 32 |
+
"stage_env_targets": [
|
| 33 |
+
24,
|
| 34 |
+
24,
|
| 35 |
+
24,
|
| 36 |
+
24,
|
| 37 |
+
24,
|
| 38 |
+
24,
|
| 39 |
+
16,
|
| 40 |
+
12,
|
| 41 |
+
10,
|
| 42 |
+
12,
|
| 43 |
+
10,
|
| 44 |
+
8,
|
| 45 |
+
8,
|
| 46 |
+
8,
|
| 47 |
+
8
|
| 48 |
+
],
|
| 49 |
+
"envs_per_shard": 20,
|
| 50 |
+
"requested_env_target": null
|
| 51 |
+
}
|