Hugging Face's logo

djmango
/
openfront-rl

Reinforcement Learning
Safetensors
PyTorch
ppo
openfront
game-ai
Model card Files
xet
 Community
djmango commited on
Commit
d9190a3
·
verified ·
1 Parent(s): e5b5413

Prune dense checkpoints (batch 29, 200 files)

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. ppo_v84/policy_update450.state.json +0 -90
  2. ppo_v84/policy_update455.safetensors +0 -3
  3. ppo_v84/policy_update455.state.json +0 -92
  4. ppo_v84/policy_update460.safetensors +0 -3
  5. ppo_v84/policy_update460.state.json +0 -94
  6. ppo_v84/policy_update465.safetensors +0 -3
  7. ppo_v84/policy_update465.state.json +0 -96
  8. ppo_v84/policy_update470.safetensors +0 -3
  9. ppo_v84/policy_update470.state.json +0 -97
  10. ppo_v84/policy_update475.safetensors +0 -3
  11. ppo_v84/policy_update475.state.json +0 -98
  12. ppo_v84/policy_update480.safetensors +0 -3
  13. ppo_v84/policy_update480.state.json +0 -99
  14. ppo_v84/policy_update485.safetensors +0 -3
  15. ppo_v84/policy_update485.state.json +0 -99
  16. ppo_v84/policy_update490.safetensors +0 -3
  17. ppo_v84/policy_update490.state.json +0 -101
  18. ppo_v84/policy_update495.safetensors +0 -3
  19. ppo_v84/policy_update495.state.json +0 -105
  20. ppo_v84/policy_update500.safetensors +0 -3
  21. ppo_v84/policy_update500.state.json +0 -109
  22. ppo_v84/policy_update505.safetensors +0 -3
  23. ppo_v84/policy_update505.state.json +0 -110
  24. ppo_v84/policy_update510.safetensors +0 -3
  25. ppo_v84/policy_update510.state.json +0 -112
  26. ppo_v84/policy_update515.safetensors +0 -3
  27. ppo_v84/policy_update515.state.json +0 -112
  28. ppo_v84/policy_update520.safetensors +0 -3
  29. ppo_v84/policy_update520.state.json +0 -113
  30. ppo_v84/policy_update525.safetensors +0 -3
  31. ppo_v84/policy_update525.state.json +0 -115
  32. ppo_v84/policy_update530.safetensors +0 -3
  33. ppo_v84/policy_update530.state.json +0 -117
  34. ppo_v84/policy_update535.safetensors +0 -3
  35. ppo_v84/policy_update535.state.json +0 -118
  36. ppo_v84/policy_update540.safetensors +0 -3
  37. ppo_v84/policy_update540.state.json +0 -118
  38. ppo_v85/policy_update545.safetensors +0 -3
  39. ppo_v85/policy_update545.state.json +0 -118
  40. ppo_v85/policy_update550.safetensors +0 -3
  41. ppo_v85/policy_update550.state.json +0 -118
  42. ppo_v85/policy_update555.safetensors +0 -3
  43. ppo_v85/policy_update555.state.json +0 -118
  44. ppo_v85/policy_update560.safetensors +0 -3
  45. ppo_v85/policy_update560.state.json +0 -118
  46. ppo_v85/policy_update565.safetensors +0 -3
  47. ppo_v85/policy_update565.state.json +0 -118
  48. ppo_v85/policy_update570.safetensors +0 -3
  49. ppo_v85/policy_update570.state.json +0 -118
  50. ppo_v85/policy_update575.safetensors +0 -3
ppo_v84/policy_update450.state.json DELETED
@@ -1,90 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 451,
5
- "stage": 8,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1028096,
9
- "recent_wins": [
10
- 1.0,
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
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 1.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 1.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 1.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 1.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 0.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0
64
- ],
65
- "best_eval_win": null,
66
- "best_eval_score": null,
67
- "v81_curriculum": true,
68
- "curriculum_schedule": "v8.3",
69
- "reward_profile": "v8.4-boat-tempo-v1",
70
- "return_stats": null,
71
- "stage_env_targets": [
72
- 24,
73
- 24,
74
- 24,
75
- 24,
76
- 24,
77
- 24,
78
- 16,
79
- 12,
80
- 10,
81
- 12,
82
- 10,
83
- 8,
84
- 8,
85
- 8,
86
- 8
87
- ],
88
- "envs_per_shard": 10,
89
- "requested_env_target": null
90
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v84/policy_update455.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e84c4ff01c192ddabaa20946aaacd24d3e26895f0d7e1e37e752548baaf0188e
3
- size 48494336
 
 
 
 
ppo_v84/policy_update455.state.json DELETED
@@ -1,92 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 456,
5
- "stage": 8,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1040896,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 1.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 1.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 1.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 1.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 0.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 1.0
66
- ],
67
- "best_eval_win": null,
68
- "best_eval_score": null,
69
- "v81_curriculum": true,
70
- "curriculum_schedule": "v8.3",
71
- "reward_profile": "v8.4-boat-tempo-v1",
72
- "return_stats": null,
73
- "stage_env_targets": [
74
- 24,
75
- 24,
76
- 24,
77
- 24,
78
- 24,
79
- 24,
80
- 16,
81
- 12,
82
- 10,
83
- 12,
84
- 10,
85
- 8,
86
- 8,
87
- 8,
88
- 8
89
- ],
90
- "envs_per_shard": 10,
91
- "requested_env_target": null
92
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v84/policy_update460.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e5b455c776afcca1e5a43fb6462c1b871feddfb5f3898f658695d9e091e9245
3
- size 48494336
 
 
 
 
ppo_v84/policy_update460.state.json DELETED
@@ -1,94 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 461,
5
- "stage": 8,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1053696,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 1.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 1.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 1.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 0.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 0.0,
67
- 1.0
68
- ],
69
- "best_eval_win": null,
70
- "best_eval_score": null,
71
- "v81_curriculum": true,
72
- "curriculum_schedule": "v8.3",
73
- "reward_profile": "v8.4-boat-tempo-v1",
74
- "return_stats": null,
75
- "stage_env_targets": [
76
- 24,
77
- 24,
78
- 24,
79
- 24,
80
- 24,
81
- 24,
82
- 16,
83
- 12,
84
- 10,
85
- 12,
86
- 10,
87
- 8,
88
- 8,
89
- 8,
90
- 8
91
- ],
92
- "envs_per_shard": 10,
93
- "requested_env_target": null
94
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v84/policy_update465.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3032b2715c4a8e72075132d51bf47af1fdaae0667e75c3b79ce8c91ed7e36a07
3
- size 48494336
 
 
 
 
ppo_v84/policy_update465.state.json DELETED
@@ -1,96 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 466,
5
- "stage": 8,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1066496,
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
- 1.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 1.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 1.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 1.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 0.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 0.0,
67
- 1.0,
68
- 1.0,
69
- 1.0
70
- ],
71
- "best_eval_win": null,
72
- "best_eval_score": null,
73
- "v81_curriculum": true,
74
- "curriculum_schedule": "v8.3",
75
- "reward_profile": "v8.4-boat-tempo-v1",
76
- "return_stats": null,
77
- "stage_env_targets": [
78
- 24,
79
- 24,
80
- 24,
81
- 24,
82
- 24,
83
- 24,
84
- 16,
85
- 12,
86
- 10,
87
- 12,
88
- 10,
89
- 8,
90
- 8,
91
- 8,
92
- 8
93
- ],
94
- "envs_per_shard": 10,
95
- "requested_env_target": null
96
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v84/policy_update470.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:03728ae9c3977b3eb48bfd16e9aa3cf30f6f1c860b48cc9f5ada0524d5731d84
3
- size 48494336
 
 
 
 
ppo_v84/policy_update470.state.json DELETED
@@ -1,97 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 471,
5
- "stage": 8,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1079296,
9
- "recent_wins": [
10
- 1.0,
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
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 1.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 1.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 1.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 0.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 0.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 0.0
71
- ],
72
- "best_eval_win": null,
73
- "best_eval_score": null,
74
- "v81_curriculum": true,
75
- "curriculum_schedule": "v8.3",
76
- "reward_profile": "v8.4-boat-tempo-v1",
77
- "return_stats": null,
78
- "stage_env_targets": [
79
- 24,
80
- 24,
81
- 24,
82
- 24,
83
- 24,
84
- 24,
85
- 16,
86
- 12,
87
- 10,
88
- 12,
89
- 10,
90
- 8,
91
- 8,
92
- 8,
93
- 8
94
- ],
95
- "envs_per_shard": 10,
96
- "requested_env_target": null
97
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v84/policy_update475.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff1a87034787523cbcdcc6aedc0d9466b3e12a634ab8716ad5e91b2904948f24
3
- size 48494336
 
 
 
 
ppo_v84/policy_update475.state.json DELETED
@@ -1,98 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 476,
5
- "stage": 8,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1092096,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 1.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 1.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 1.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 1.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 0.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 0.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 0.0,
71
- 1.0
72
- ],
73
- "best_eval_win": null,
74
- "best_eval_score": null,
75
- "v81_curriculum": true,
76
- "curriculum_schedule": "v8.3",
77
- "reward_profile": "v8.4-boat-tempo-v1",
78
- "return_stats": null,
79
- "stage_env_targets": [
80
- 24,
81
- 24,
82
- 24,
83
- 24,
84
- 24,
85
- 24,
86
- 16,
87
- 12,
88
- 10,
89
- 12,
90
- 10,
91
- 8,
92
- 8,
93
- 8,
94
- 8
95
- ],
96
- "envs_per_shard": 10,
97
- "requested_env_target": null
98
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v84/policy_update480.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5717a3249bc681e406c9bb986450f9da9feb50f52a85eca69d575dbaeace42dc
3
- size 48494336
 
 
 
 
ppo_v84/policy_update480.state.json DELETED
@@ -1,99 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 481,
5
- "stage": 8,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1104896,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 1.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 1.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 1.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 0.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 0.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 0.0,
71
- 1.0,
72
- 0.0
73
- ],
74
- "best_eval_win": null,
75
- "best_eval_score": null,
76
- "v81_curriculum": true,
77
- "curriculum_schedule": "v8.3",
78
- "reward_profile": "v8.4-boat-tempo-v1",
79
- "return_stats": null,
80
- "stage_env_targets": [
81
- 24,
82
- 24,
83
- 24,
84
- 24,
85
- 24,
86
- 24,
87
- 16,
88
- 12,
89
- 10,
90
- 12,
91
- 10,
92
- 8,
93
- 8,
94
- 8,
95
- 8
96
- ],
97
- "envs_per_shard": 10,
98
- "requested_env_target": null
99
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v84/policy_update485.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fc429aad6c53eb16b6fb897135a54348b34c8e5161cb7184f65f997c600604e
3
- size 48494336
 
 
 
 
ppo_v84/policy_update485.state.json DELETED
@@ -1,99 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 486,
5
- "stage": 8,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1117696,
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
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 1.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 0.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 0.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 0.0,
71
- 1.0,
72
- 0.0
73
- ],
74
- "best_eval_win": null,
75
- "best_eval_score": null,
76
- "v81_curriculum": true,
77
- "curriculum_schedule": "v8.3",
78
- "reward_profile": "v8.4-boat-tempo-v1",
79
- "return_stats": null,
80
- "stage_env_targets": [
81
- 24,
82
- 24,
83
- 24,
84
- 24,
85
- 24,
86
- 24,
87
- 16,
88
- 12,
89
- 10,
90
- 12,
91
- 10,
92
- 8,
93
- 8,
94
- 8,
95
- 8
96
- ],
97
- "envs_per_shard": 10,
98
- "requested_env_target": null
99
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v84/policy_update490.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7dc53377caf559be118143dda9f5d0fb3cd68431be343cefe24996cf56f3bb63
3
- size 48494336
 
 
 
 
ppo_v84/policy_update490.state.json DELETED
@@ -1,101 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 491,
5
- "stage": 8,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1130496,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 1.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 1.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 0.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 0.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 0.0,
71
- 1.0,
72
- 0.0,
73
- 0.0,
74
- 1.0
75
- ],
76
- "best_eval_win": null,
77
- "best_eval_score": null,
78
- "v81_curriculum": true,
79
- "curriculum_schedule": "v8.3",
80
- "reward_profile": "v8.4-boat-tempo-v1",
81
- "return_stats": null,
82
- "stage_env_targets": [
83
- 24,
84
- 24,
85
- 24,
86
- 24,
87
- 24,
88
- 24,
89
- 16,
90
- 12,
91
- 10,
92
- 12,
93
- 10,
94
- 8,
95
- 8,
96
- 8,
97
- 8
98
- ],
99
- "envs_per_shard": 10,
100
- "requested_env_target": null
101
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v84/policy_update495.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e227a8f53e119662237ddec7a35b242d4b2ef89f2a4a0396896de46cdbf1f27
3
- size 48494336
 
 
 
 
ppo_v84/policy_update495.state.json DELETED
@@ -1,105 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 496,
5
- "stage": 8,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1143296,
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
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 1.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 1.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 1.0,
47
- 0.0,
48
- 1.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 0.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 0.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 0.0,
71
- 1.0,
72
- 0.0,
73
- 0.0,
74
- 1.0,
75
- 1.0,
76
- 0.0,
77
- 1.0,
78
- 1.0
79
- ],
80
- "best_eval_win": null,
81
- "best_eval_score": null,
82
- "v81_curriculum": true,
83
- "curriculum_schedule": "v8.3",
84
- "reward_profile": "v8.4-boat-tempo-v1",
85
- "return_stats": null,
86
- "stage_env_targets": [
87
- 24,
88
- 24,
89
- 24,
90
- 24,
91
- 24,
92
- 24,
93
- 16,
94
- 12,
95
- 10,
96
- 12,
97
- 10,
98
- 8,
99
- 8,
100
- 8,
101
- 8
102
- ],
103
- "envs_per_shard": 10,
104
- "requested_env_target": null
105
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v84/policy_update500.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d89d4674d5466745b13cf381eaf7bc9fbc7ef594ff64604997c6a1572d388427
3
- size 48494336
 
 
 
 
ppo_v84/policy_update500.state.json DELETED
@@ -1,109 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 501,
5
- "stage": 8,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1156096,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 1.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 1.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 1.0,
28
- 0.0,
29
- 1.0,
30
- 0.0,
31
- 0.0,
32
- 1.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 1.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 0.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 0.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 0.0,
71
- 1.0,
72
- 0.0,
73
- 0.0,
74
- 1.0,
75
- 1.0,
76
- 0.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 0.0,
81
- 0.0,
82
- 1.0
83
- ],
84
- "best_eval_win": null,
85
- "best_eval_score": null,
86
- "v81_curriculum": true,
87
- "curriculum_schedule": "v8.3",
88
- "reward_profile": "v8.4-boat-tempo-v1",
89
- "return_stats": null,
90
- "stage_env_targets": [
91
- 24,
92
- 24,
93
- 24,
94
- 24,
95
- 24,
96
- 24,
97
- 16,
98
- 12,
99
- 10,
100
- 12,
101
- 10,
102
- 8,
103
- 8,
104
- 8,
105
- 8
106
- ],
107
- "envs_per_shard": 10,
108
- "requested_env_target": null
109
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v84/policy_update505.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9a5a1126f0888a8305b79960b115dde6856a2f977c12c5201bcd8ff79e521e9
3
- size 48494336
 
 
 
 
ppo_v84/policy_update505.state.json DELETED
@@ -1,110 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 506,
5
- "stage": 8,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1168896,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 1.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 1.0,
23
- 0.0,
24
- 1.0,
25
- 0.0,
26
- 0.0,
27
- 1.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 1.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 0.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 0.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 0.0,
71
- 1.0,
72
- 0.0,
73
- 0.0,
74
- 1.0,
75
- 1.0,
76
- 0.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 0.0,
81
- 0.0,
82
- 1.0,
83
- 0.0
84
- ],
85
- "best_eval_win": null,
86
- "best_eval_score": null,
87
- "v81_curriculum": true,
88
- "curriculum_schedule": "v8.3",
89
- "reward_profile": "v8.4-boat-tempo-v1",
90
- "return_stats": null,
91
- "stage_env_targets": [
92
- 24,
93
- 24,
94
- 24,
95
- 24,
96
- 24,
97
- 24,
98
- 16,
99
- 12,
100
- 10,
101
- 12,
102
- 10,
103
- 8,
104
- 8,
105
- 8,
106
- 8
107
- ],
108
- "envs_per_shard": 10,
109
- "requested_env_target": null
110
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v84/policy_update510.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d916ecf2dd4753a53c536826a1f04c68c8fa0131f9c9fb4c233ed38f5ad579f
3
- size 48494336
 
 
 
 
ppo_v84/policy_update510.state.json DELETED
@@ -1,112 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 511,
5
- "stage": 8,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1181696,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 0.0,
13
- 1.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 1.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 1.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 1.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 0.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 0.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 0.0,
71
- 1.0,
72
- 0.0,
73
- 0.0,
74
- 1.0,
75
- 1.0,
76
- 0.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 0.0,
81
- 0.0,
82
- 1.0,
83
- 0.0,
84
- 1.0,
85
- 1.0
86
- ],
87
- "best_eval_win": null,
88
- "best_eval_score": null,
89
- "v81_curriculum": true,
90
- "curriculum_schedule": "v8.3",
91
- "reward_profile": "v8.4-boat-tempo-v1",
92
- "return_stats": null,
93
- "stage_env_targets": [
94
- 24,
95
- 24,
96
- 24,
97
- 24,
98
- 24,
99
- 24,
100
- 16,
101
- 12,
102
- 10,
103
- 12,
104
- 10,
105
- 8,
106
- 8,
107
- 8,
108
- 8
109
- ],
110
- "envs_per_shard": 10,
111
- "requested_env_target": null
112
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v84/policy_update515.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:698df1ecc5f4e5662b4802890131bf2eb107655f49a6033f8fbbad680b58ffe5
3
- size 48494336
 
 
 
 
ppo_v84/policy_update515.state.json DELETED
@@ -1,112 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 516,
5
- "stage": 8,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1194496,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 1.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 1.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 1.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 0.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 0.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 0.0,
71
- 1.0,
72
- 0.0,
73
- 0.0,
74
- 1.0,
75
- 1.0,
76
- 0.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 0.0,
81
- 0.0,
82
- 1.0,
83
- 0.0,
84
- 1.0,
85
- 1.0
86
- ],
87
- "best_eval_win": null,
88
- "best_eval_score": null,
89
- "v81_curriculum": true,
90
- "curriculum_schedule": "v8.3",
91
- "reward_profile": "v8.4-boat-tempo-v1",
92
- "return_stats": null,
93
- "stage_env_targets": [
94
- 24,
95
- 24,
96
- 24,
97
- 24,
98
- 24,
99
- 24,
100
- 16,
101
- 12,
102
- 10,
103
- 12,
104
- 10,
105
- 8,
106
- 8,
107
- 8,
108
- 8
109
- ],
110
- "envs_per_shard": 10,
111
- "requested_env_target": null
112
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v84/policy_update520.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd450369b792930c49b630a1540c54a049caa01965c9fbaffcd60b48dcb2ecca
3
- size 48494336
 
 
 
 
ppo_v84/policy_update520.state.json DELETED
@@ -1,113 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 521,
5
- "stage": 8,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1207296,
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
- 1.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 1.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 1.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 0.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 0.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 0.0,
71
- 1.0,
72
- 0.0,
73
- 0.0,
74
- 1.0,
75
- 1.0,
76
- 0.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 0.0,
81
- 0.0,
82
- 1.0,
83
- 0.0,
84
- 1.0,
85
- 1.0,
86
- 1.0
87
- ],
88
- "best_eval_win": null,
89
- "best_eval_score": null,
90
- "v81_curriculum": true,
91
- "curriculum_schedule": "v8.3",
92
- "reward_profile": "v8.4-boat-tempo-v1",
93
- "return_stats": null,
94
- "stage_env_targets": [
95
- 24,
96
- 24,
97
- 24,
98
- 24,
99
- 24,
100
- 24,
101
- 16,
102
- 12,
103
- 10,
104
- 12,
105
- 10,
106
- 8,
107
- 8,
108
- 8,
109
- 8
110
- ],
111
- "envs_per_shard": 10,
112
- "requested_env_target": null
113
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v84/policy_update525.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3622c82f385e181e2189e1c83c367792ebee318a950c0816f4aa883bc1ed98a
3
- size 48494336
 
 
 
 
ppo_v84/policy_update525.state.json DELETED
@@ -1,115 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 526,
5
- "stage": 8,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1220096,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 1.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 1.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 0.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 0.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 0.0,
71
- 1.0,
72
- 0.0,
73
- 0.0,
74
- 1.0,
75
- 1.0,
76
- 0.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 0.0,
81
- 0.0,
82
- 1.0,
83
- 0.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 0.0,
88
- 1.0
89
- ],
90
- "best_eval_win": null,
91
- "best_eval_score": null,
92
- "v81_curriculum": true,
93
- "curriculum_schedule": "v8.3",
94
- "reward_profile": "v8.4-boat-tempo-v1",
95
- "return_stats": null,
96
- "stage_env_targets": [
97
- 24,
98
- 24,
99
- 24,
100
- 24,
101
- 24,
102
- 24,
103
- 16,
104
- 12,
105
- 10,
106
- 12,
107
- 10,
108
- 8,
109
- 8,
110
- 8,
111
- 8
112
- ],
113
- "envs_per_shard": 10,
114
- "requested_env_target": null
115
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v84/policy_update530.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1259ce7e756311d99fd959aeb3a20915a921dfa080bce636916e14c3905e130
3
- size 48494336
 
 
 
 
ppo_v84/policy_update530.state.json DELETED
@@ -1,117 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 531,
5
- "stage": 8,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1232896,
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
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 1.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 1.0,
41
- 1.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 0.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 0.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 0.0,
71
- 1.0,
72
- 0.0,
73
- 0.0,
74
- 1.0,
75
- 1.0,
76
- 0.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 0.0,
81
- 0.0,
82
- 1.0,
83
- 0.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 0.0,
88
- 1.0,
89
- 1.0,
90
- 0.0
91
- ],
92
- "best_eval_win": null,
93
- "best_eval_score": null,
94
- "v81_curriculum": true,
95
- "curriculum_schedule": "v8.3",
96
- "reward_profile": "v8.4-boat-tempo-v1",
97
- "return_stats": null,
98
- "stage_env_targets": [
99
- 24,
100
- 24,
101
- 24,
102
- 24,
103
- 24,
104
- 24,
105
- 16,
106
- 12,
107
- 10,
108
- 12,
109
- 10,
110
- 8,
111
- 8,
112
- 8,
113
- 8
114
- ],
115
- "envs_per_shard": 10,
116
- "requested_env_target": null
117
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v84/policy_update535.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c73bcb71892297cc89b010b61e0de183175f70bc88d913cc33b56d17d514a81f
3
- size 48494336
 
 
 
 
ppo_v84/policy_update535.state.json DELETED
@@ -1,118 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 536,
5
- "stage": 8,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1245696,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 1.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 1.0,
30
- 1.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 1.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 1.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 0.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 0.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 0.0,
64
- 1.0,
65
- 0.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 0.0,
70
- 1.0,
71
- 0.0,
72
- 0.0,
73
- 1.0,
74
- 1.0,
75
- 0.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 0.0,
80
- 0.0,
81
- 1.0,
82
- 0.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 0.0,
87
- 1.0,
88
- 1.0,
89
- 0.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "best_eval_win": null,
94
- "best_eval_score": null,
95
- "v81_curriculum": true,
96
- "curriculum_schedule": "v8.3",
97
- "reward_profile": "v8.4-boat-tempo-v1",
98
- "return_stats": null,
99
- "stage_env_targets": [
100
- 24,
101
- 24,
102
- 24,
103
- 24,
104
- 24,
105
- 24,
106
- 16,
107
- 12,
108
- 10,
109
- 12,
110
- 10,
111
- 8,
112
- 8,
113
- 8,
114
- 8
115
- ],
116
- "envs_per_shard": 10,
117
- "requested_env_target": null
118
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v84/policy_update540.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:afa8639ee101b11d6e433215209aca744ac34d6a3e9f5be2e9fd0edf9b57558d
3
- size 48494336
 
 
 
 
ppo_v84/policy_update540.state.json DELETED
@@ -1,118 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 541,
5
- "stage": 8,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1258496,
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
- 1.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 1.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 1.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 0.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 0.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 0.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 0.0,
69
- 1.0,
70
- 0.0,
71
- 0.0,
72
- 1.0,
73
- 1.0,
74
- 0.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 0.0,
79
- 0.0,
80
- 1.0,
81
- 0.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 0.0,
86
- 1.0,
87
- 1.0,
88
- 0.0,
89
- 1.0,
90
- 1.0,
91
- 0.0
92
- ],
93
- "best_eval_win": null,
94
- "best_eval_score": null,
95
- "v81_curriculum": true,
96
- "curriculum_schedule": "v8.3",
97
- "reward_profile": "v8.4-boat-tempo-v1",
98
- "return_stats": null,
99
- "stage_env_targets": [
100
- 24,
101
- 24,
102
- 24,
103
- 24,
104
- 24,
105
- 24,
106
- 16,
107
- 12,
108
- 10,
109
- 12,
110
- 10,
111
- 8,
112
- 8,
113
- 8,
114
- 8
115
- ],
116
- "envs_per_shard": 10,
117
- "requested_env_target": null
118
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v85/policy_update545.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf7c2154862afd4d8cb8bf4db7515a2ff339cc4de4151860438759c340520658
3
- size 48494336
 
 
 
 
ppo_v85/policy_update545.state.json DELETED
@@ -1,118 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 546,
5
- "stage": 8,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1271296,
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
- 1.0,
19
- 1.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 1.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 1.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 0.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 0.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 0.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 0.0,
69
- 1.0,
70
- 0.0,
71
- 0.0,
72
- 1.0,
73
- 1.0,
74
- 0.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 0.0,
79
- 0.0,
80
- 1.0,
81
- 0.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 0.0,
86
- 1.0,
87
- 1.0,
88
- 0.0,
89
- 1.0,
90
- 1.0,
91
- 0.0
92
- ],
93
- "best_eval_win": null,
94
- "best_eval_score": null,
95
- "v81_curriculum": true,
96
- "curriculum_schedule": "v8.3",
97
- "reward_profile": "v8.5-win-urgency-v1",
98
- "return_stats": null,
99
- "stage_env_targets": [
100
- 24,
101
- 24,
102
- 24,
103
- 24,
104
- 24,
105
- 24,
106
- 16,
107
- 12,
108
- 10,
109
- 12,
110
- 10,
111
- 8,
112
- 8,
113
- 8,
114
- 8
115
- ],
116
- "envs_per_shard": 10,
117
- "requested_env_target": null
118
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v85/policy_update550.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9573fc0676faf21baf6d85699cc967cfff47fac2a02f40523613b1edc681b3bf
3
- size 48494336
 
 
 
 
ppo_v85/policy_update550.state.json DELETED
@@ -1,118 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 551,
5
- "stage": 8,
6
- "ent_scale": 1.6095238095238096,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1284096,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 1.0,
13
- 1.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 1.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 1.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 0.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 0.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 0.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 0.0,
69
- 1.0,
70
- 0.0,
71
- 0.0,
72
- 1.0,
73
- 1.0,
74
- 0.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 0.0,
79
- 0.0,
80
- 1.0,
81
- 0.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 0.0,
86
- 1.0,
87
- 1.0,
88
- 0.0,
89
- 1.0,
90
- 1.0,
91
- 0.0
92
- ],
93
- "best_eval_win": null,
94
- "best_eval_score": null,
95
- "v81_curriculum": true,
96
- "curriculum_schedule": "v8.3",
97
- "reward_profile": "v8.5-win-urgency-v1",
98
- "return_stats": null,
99
- "stage_env_targets": [
100
- 24,
101
- 24,
102
- 24,
103
- 24,
104
- 24,
105
- 24,
106
- 16,
107
- 12,
108
- 10,
109
- 12,
110
- 10,
111
- 8,
112
- 8,
113
- 8,
114
- 8
115
- ],
116
- "envs_per_shard": 10,
117
- "requested_env_target": null
118
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v85/policy_update555.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:203ea26a204df5d81327fe7b41993e3f01556a1b182553279a84fd923d79eae3
3
- size 48494336
 
 
 
 
ppo_v85/policy_update555.state.json DELETED
@@ -1,118 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 556,
5
- "stage": 8,
6
- "ent_scale": 2.349720538253094,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1296896,
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
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 1.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 1.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 0.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 0.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 0.0,
62
- 1.0,
63
- 0.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 0.0,
68
- 1.0,
69
- 0.0,
70
- 0.0,
71
- 1.0,
72
- 1.0,
73
- 0.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 0.0,
78
- 0.0,
79
- 1.0,
80
- 0.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 0.0,
85
- 1.0,
86
- 1.0,
87
- 0.0,
88
- 1.0,
89
- 1.0,
90
- 0.0,
91
- 1.0
92
- ],
93
- "best_eval_win": null,
94
- "best_eval_score": null,
95
- "v81_curriculum": true,
96
- "curriculum_schedule": "v8.3",
97
- "reward_profile": "v8.5-win-urgency-v1",
98
- "return_stats": null,
99
- "stage_env_targets": [
100
- 24,
101
- 24,
102
- 24,
103
- 24,
104
- 24,
105
- 24,
106
- 16,
107
- 12,
108
- 10,
109
- 12,
110
- 10,
111
- 8,
112
- 8,
113
- 8,
114
- 8
115
- ],
116
- "envs_per_shard": 10,
117
- "requested_env_target": null
118
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v85/policy_update560.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5620b7b3f9c69ba5430ada34b638ff5cd8c98bc1a722dcdedeada9ff4c83106a
3
- size 48494336
 
 
 
 
ppo_v85/policy_update560.state.json DELETED
@@ -1,118 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 561,
5
- "stage": 8,
6
- "ent_scale": 2.5130571724571733,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1309696,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 1.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 1.0,
36
- 0.0,
37
- 0.0,
38
- 1.0,
39
- 0.0,
40
- 0.0,
41
- 1.0,
42
- 1.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 0.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 0.0,
59
- 1.0,
60
- 0.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 0.0,
67
- 0.0,
68
- 1.0,
69
- 1.0,
70
- 0.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 0.0,
75
- 0.0,
76
- 1.0,
77
- 0.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 0.0,
82
- 1.0,
83
- 1.0,
84
- 0.0,
85
- 1.0,
86
- 1.0,
87
- 0.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "best_eval_win": null,
94
- "best_eval_score": null,
95
- "v81_curriculum": true,
96
- "curriculum_schedule": "v8.3",
97
- "reward_profile": "v8.5-win-urgency-v1",
98
- "return_stats": null,
99
- "stage_env_targets": [
100
- 24,
101
- 24,
102
- 24,
103
- 24,
104
- 24,
105
- 24,
106
- 16,
107
- 12,
108
- 10,
109
- 12,
110
- 10,
111
- 8,
112
- 8,
113
- 8,
114
- 8
115
- ],
116
- "envs_per_shard": 10,
117
- "requested_env_target": null
118
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v85/policy_update565.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9d45d1e953ff9aaf9c017ea6b5de39e2036c5d64540ee7f1d26f4cd06945551
3
- size 48494336
 
 
 
 
ppo_v85/policy_update565.state.json DELETED
@@ -1,118 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 566,
5
- "stage": 8,
6
- "ent_scale": 1.969046052451434,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1322496,
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
- 0.0,
21
- 0.0,
22
- 1.0,
23
- 0.0,
24
- 0.0,
25
- 1.0,
26
- 0.0,
27
- 0.0,
28
- 1.0,
29
- 1.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 1.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 0.0,
57
- 1.0,
58
- 0.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 0.0,
63
- 1.0,
64
- 0.0,
65
- 0.0,
66
- 1.0,
67
- 1.0,
68
- 0.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 0.0,
73
- 0.0,
74
- 1.0,
75
- 0.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 0.0,
80
- 1.0,
81
- 1.0,
82
- 0.0,
83
- 1.0,
84
- 1.0,
85
- 0.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 0.0
92
- ],
93
- "best_eval_win": null,
94
- "best_eval_score": null,
95
- "v81_curriculum": true,
96
- "curriculum_schedule": "v8.3",
97
- "reward_profile": "v8.5-win-urgency-v1",
98
- "return_stats": null,
99
- "stage_env_targets": [
100
- 24,
101
- 24,
102
- 24,
103
- 24,
104
- 24,
105
- 24,
106
- 16,
107
- 12,
108
- 10,
109
- 12,
110
- 10,
111
- 8,
112
- 8,
113
- 8,
114
- 8
115
- ],
116
- "envs_per_shard": 10,
117
- "requested_env_target": null
118
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v85/policy_update570.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bf5de1505ff6c2a06db48d4615ec97c519924a0137f82544888212e18821741
3
- size 48494336
 
 
 
 
ppo_v85/policy_update570.state.json DELETED
@@ -1,118 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 571,
5
- "stage": 8,
6
- "ent_scale": 1.542799105077124,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1335296,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 1.0,
16
- 0.0,
17
- 0.0,
18
- 1.0,
19
- 0.0,
20
- 0.0,
21
- 1.0,
22
- 1.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 1.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 1.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 0.0,
56
- 1.0,
57
- 0.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 0.0,
62
- 1.0,
63
- 0.0,
64
- 0.0,
65
- 1.0,
66
- 1.0,
67
- 0.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 0.0,
72
- 0.0,
73
- 1.0,
74
- 0.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 0.0,
79
- 1.0,
80
- 1.0,
81
- 0.0,
82
- 1.0,
83
- 1.0,
84
- 0.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 0.0,
91
- 1.0
92
- ],
93
- "best_eval_win": null,
94
- "best_eval_score": null,
95
- "v81_curriculum": true,
96
- "curriculum_schedule": "v8.3",
97
- "reward_profile": "v8.5-win-urgency-v1",
98
- "return_stats": null,
99
- "stage_env_targets": [
100
- 24,
101
- 24,
102
- 24,
103
- 24,
104
- 24,
105
- 24,
106
- 16,
107
- 12,
108
- 10,
109
- 12,
110
- 10,
111
- 8,
112
- 8,
113
- 8,
114
- 8
115
- ],
116
- "envs_per_shard": 10,
117
- "requested_env_target": null
118
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v85/policy_update575.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a593324ed30b31b4bf0ba2279d62ee8ee28c798d13a3363726f7f8d59c5169f4
3
- size 48494336