Muqeeth commited on
Commit
f4a4fb9
·
verified ·
1 Parent(s): 563b0f5

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. seed_1000/iteration_234/agent:Alice_rewards.csv +64 -0
  2. seed_1000/iteration_234/agent:Bob_rewards.csv +64 -0
  3. seed_1000/iteration_234/agent_trainer_log/basic_training_metrics_2025-08-20___11-52-30.json +44 -0
  4. seed_1000/iteration_234/mgid:10439309_rollout_tree.json +0 -0
  5. seed_1000/iteration_234/mgid:12516741_rollout_tree.json +0 -0
  6. seed_1000/iteration_234/mgid:16202745_rollout_tree.json +0 -0
  7. seed_1000/iteration_234/mgid:16393071_rollout_tree.json +0 -0
  8. seed_1000/iteration_234/mgid:18921560_rollout_tree.json +0 -0
  9. seed_1000/iteration_234/mgid:30538311_rollout_tree.json +0 -0
  10. seed_1000/iteration_234/mgid:32264805_rollout_tree.json +0 -0
  11. seed_1000/iteration_234/mgid:32460192_rollout_tree.json +0 -0
  12. seed_1000/iteration_234/mgid:78941590_rollout_tree.json +0 -0
  13. seed_1000/iteration_234/mgid:89971565_rollout_tree.json +0 -0
  14. seed_1000/iteration_234/mgid:97569124_rollout_tree.json +0 -0
  15. seed_1000/iteration_235/agent:Alice_rewards.csv +64 -0
  16. seed_1000/iteration_235/agent:Bob_rewards.csv +64 -0
  17. seed_1000/iteration_235/agent_trainer_log/basic_training_metrics_2025-08-20___11-53-25.json +44 -0
  18. seed_1000/iteration_235/mgid:10105453_rollout_tree.json +0 -0
  19. seed_1000/iteration_235/mgid:10314982_rollout_tree.json +0 -0
  20. seed_1000/iteration_235/mgid:11489158_rollout_tree.json +0 -0
  21. seed_1000/iteration_235/mgid:11501742_rollout_tree.json +0 -0
  22. seed_1000/iteration_235/mgid:12022357_rollout_tree.json +0 -0
  23. seed_1000/iteration_235/mgid:12594705_rollout_tree.json +0 -0
  24. seed_1000/iteration_235/mgid:15372248_rollout_tree.json +0 -0
  25. seed_1000/iteration_235/mgid:16993941_rollout_tree.json +0 -0
  26. seed_1000/iteration_235/mgid:17018789_rollout_tree.json +0 -0
  27. seed_1000/iteration_235/mgid:17052654_rollout_tree.json +0 -0
  28. seed_1000/iteration_235/mgid:17334311_rollout_tree.json +0 -0
  29. seed_1000/iteration_235/mgid:17581887_rollout_tree.json +0 -0
  30. seed_1000/iteration_235/mgid:17679445_rollout_tree.json +0 -0
  31. seed_1000/iteration_235/mgid:18466251_rollout_tree.json +0 -0
  32. seed_1000/iteration_235/mgid:18500631_rollout_tree.json +0 -0
  33. seed_1000/iteration_235/mgid:18914909_rollout_tree.json +0 -0
  34. seed_1000/iteration_235/mgid:19746619_rollout_tree.json +0 -0
  35. seed_1000/iteration_235/mgid:20705813_rollout_tree.json +0 -0
  36. seed_1000/iteration_235/mgid:21698535_rollout_tree.json +0 -0
  37. seed_1000/iteration_235/mgid:21768341_rollout_tree.json +0 -0
  38. seed_1000/iteration_235/mgid:21771648_rollout_tree.json +0 -0
  39. seed_1000/iteration_235/mgid:22104301_rollout_tree.json +0 -0
  40. seed_1000/iteration_235/mgid:22780621_rollout_tree.json +0 -0
  41. seed_1000/iteration_235/mgid:22897858_rollout_tree.json +0 -0
  42. seed_1000/iteration_235/mgid:24628552_rollout_tree.json +0 -0
  43. seed_1000/iteration_235/mgid:24808697_rollout_tree.json +0 -0
  44. seed_1000/iteration_235/mgid:25054651_rollout_tree.json +0 -0
  45. seed_1000/iteration_235/mgid:25400228_rollout_tree.json +0 -0
  46. seed_1000/iteration_235/mgid:26333961_rollout_tree.json +0 -0
  47. seed_1000/iteration_235/mgid:26360937_rollout_tree.json +0 -0
  48. seed_1000/iteration_235/mgid:26441504_rollout_tree.json +0 -0
  49. seed_1000/iteration_235/mgid:27374421_rollout_tree.json +0 -0
  50. seed_1000/iteration_235/mgid:27603159_rollout_tree.json +0 -0
seed_1000/iteration_234/agent:Alice_rewards.csv ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 1,3,1,3,1,3,1,3,1,3
2
+ 1,5,1,1,1,1,1,1,1,1
3
+ 1,5,1,1,1,1,1,1,1,1
4
+ 1,3,1,3,1,3,1,3,1,3
5
+ 1,5,1,1,1,1,1,1,1,1
6
+ 1,3,1,3,1,3,1,3,1,3
7
+ 1,3,1,5,0,1,5,0,1,5
8
+ 1,3,1,5,0,1,5,0,1,5
9
+ 1,5,1,0,1,5,0,5,0,5
10
+ 1,3,1,3,1,3,1,3,1,3
11
+ 1,3,1,3,1,3,1,3,1,3
12
+ 1,3,1,3,1,3,1,3,1,3
13
+ 1,3,1,0,5,1,0,5,1,0
14
+ 1,3,1,0,5,1,0,5,1,0
15
+ 1,3,1,3,1,3,1,3,1,3
16
+ 1,0,1,1,1,1,1,1,1,1
17
+ 1,5,1,1,1,1,1,1,1,1
18
+ 1,1,1,1,1,1,1,1,1,1
19
+ 1,3,1,3,1,3,1,3,1,3
20
+ 1,5,1,1,1,1,1,1,1,1
21
+ 1,3,1,3,1,3,1,3,1,3
22
+ 1,3,1,5,0,1,5,0,1,5
23
+ 1,0,1,1,1,1,1,1,1,1
24
+ 1,3,1,0,5,1,0,5,1,0
25
+ 1,5,1,1,1,1,1,1,1,1
26
+ 1,3,1,0,5,1,0,5,1,0
27
+ 1,3,1,3,1,3,1,3,1,3
28
+ 1,3,1,3,1,3,1,3,1,3
29
+ 1,5,1,5,1,1,1,1,1,1
30
+ 1,3,1,3,1,3,1,3,1,3
31
+ 1,0,1,1,1,1,1,1,1,1
32
+ 1,3,1,5,0,1,5,0,1,5
33
+ 1,1,1,1,1,1,1,1,1,1
34
+ 1,3,1,3,1,3,1,3,1,3
35
+ 1,3,1,3,1,3,1,3,1,3
36
+ 1,3,1,3,1,3,1,3,1,3
37
+ 1,3,1,3,1,3,1,3,1,3
38
+ 1,1,1,1,1,1,1,1,1,1
39
+ 1,3,1,3,1,3,1,3,1,3
40
+ 1,3,1,3,1,3,1,3,1,3
41
+ 1,3,1,5,0,1,5,0,1,5
42
+ 1,0,5,1,0,5,1,0,5,1
43
+ 1,3,1,3,1,3,1,3,1,3
44
+ 1,5,1,1,1,1,1,1,1,1
45
+ 1,3,1,5,0,1,5,0,1,5
46
+ 1,3,1,3,1,3,1,3,1,3
47
+ 1,3,1,3,1,3,1,3,1,3
48
+ 1,5,1,1,1,1,1,1,1,1
49
+ 1,3,1,3,1,3,1,3,1,3
50
+ 1,3,1,3,1,3,1,3,1,3
51
+ 1,3,1,3,1,3,1,3,1,3
52
+ 1,3,1,3,1,3,1,3,1,3
53
+ 1,0,1,1,1,1,1,1,1,1
54
+ 1,0,1,1,1,1,1,1,1,1
55
+ 1,3,1,3,1,3,1,3,1,3
56
+ 1,0,1,1,1,1,1,1,1,1
57
+ 1,3,1,5,0,1,5,0,1,5
58
+ 1,3,1,3,1,3,1,3,1,3
59
+ 1,3,1,3,1,3,1,3,1,3
60
+ 1,3,1,3,1,3,1,3,1,3
61
+ 1,3,1,3,1,3,1,3,1,3
62
+ 1,0,1,1,1,1,1,1,1,1
63
+ 1,3,1,3,1,3,1,3,1,3
64
+ 1,3,1,0,5,1,0,5,1,0
seed_1000/iteration_234/agent:Bob_rewards.csv ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 1,3,1,3,1,3,1,3,1,3
2
+ 1,0,1,1,1,1,1,1,1,1
3
+ 1,0,1,1,1,1,1,1,1,1
4
+ 1,3,1,3,1,3,1,3,1,3
5
+ 1,0,1,1,1,1,1,1,1,1
6
+ 1,3,1,3,1,3,1,3,1,3
7
+ 1,3,1,0,5,1,0,5,1,0
8
+ 1,3,1,0,5,1,0,5,1,0
9
+ 1,0,1,5,1,0,5,0,5,0
10
+ 1,3,1,3,1,3,1,3,1,3
11
+ 1,3,1,3,1,3,1,3,1,3
12
+ 1,3,1,3,1,3,1,3,1,3
13
+ 1,3,1,5,0,1,5,0,1,5
14
+ 1,3,1,5,0,1,5,0,1,5
15
+ 1,3,1,3,1,3,1,3,1,3
16
+ 1,5,1,1,1,1,1,1,1,1
17
+ 1,0,1,1,1,1,1,1,1,1
18
+ 1,1,1,1,1,1,1,1,1,1
19
+ 1,3,1,3,1,3,1,3,1,3
20
+ 1,0,1,1,1,1,1,1,1,1
21
+ 1,3,1,3,1,3,1,3,1,3
22
+ 1,3,1,0,5,1,0,5,1,0
23
+ 1,5,1,1,1,1,1,1,1,1
24
+ 1,3,1,5,0,1,5,0,1,5
25
+ 1,0,1,1,1,1,1,1,1,1
26
+ 1,3,1,5,0,1,5,0,1,5
27
+ 1,3,1,3,1,3,1,3,1,3
28
+ 1,3,1,3,1,3,1,3,1,3
29
+ 1,0,1,0,1,1,1,1,1,1
30
+ 1,3,1,3,1,3,1,3,1,3
31
+ 1,5,1,1,1,1,1,1,1,1
32
+ 1,3,1,0,5,1,0,5,1,0
33
+ 1,1,1,1,1,1,1,1,1,1
34
+ 1,3,1,3,1,3,1,3,1,3
35
+ 1,3,1,3,1,3,1,3,1,3
36
+ 1,3,1,3,1,3,1,3,1,3
37
+ 1,3,1,3,1,3,1,3,1,3
38
+ 1,1,1,1,1,1,1,1,1,1
39
+ 1,3,1,3,1,3,1,3,1,3
40
+ 1,3,1,3,1,3,1,3,1,3
41
+ 1,3,1,0,5,1,0,5,1,0
42
+ 1,5,0,1,5,0,1,5,0,1
43
+ 1,3,1,3,1,3,1,3,1,3
44
+ 1,0,1,1,1,1,1,1,1,1
45
+ 1,3,1,0,5,1,0,5,1,0
46
+ 1,3,1,3,1,3,1,3,1,3
47
+ 1,3,1,3,1,3,1,3,1,3
48
+ 1,0,1,1,1,1,1,1,1,1
49
+ 1,3,1,3,1,3,1,3,1,3
50
+ 1,3,1,3,1,3,1,3,1,3
51
+ 1,3,1,3,1,3,1,3,1,3
52
+ 1,3,1,3,1,3,1,3,1,3
53
+ 1,5,1,1,1,1,1,1,1,1
54
+ 1,5,1,1,1,1,1,1,1,1
55
+ 1,3,1,3,1,3,1,3,1,3
56
+ 1,5,1,1,1,1,1,1,1,1
57
+ 1,3,1,0,5,1,0,5,1,0
58
+ 1,3,1,3,1,3,1,3,1,3
59
+ 1,3,1,3,1,3,1,3,1,3
60
+ 1,3,1,3,1,3,1,3,1,3
61
+ 1,3,1,3,1,3,1,3,1,3
62
+ 1,5,1,1,1,1,1,1,1,1
63
+ 1,3,1,3,1,3,1,3,1,3
64
+ 1,3,1,5,0,1,5,0,1,5
seed_1000/iteration_234/agent_trainer_log/basic_training_metrics_2025-08-20___11-52-30.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "nb_rollouts": [
3
+ 128
4
+ ],
5
+ "loss_mb_total": {
6
+ "value_mb_total": [
7
+ 0.3770354092121124,
8
+ 0.24432890117168427,
9
+ 1.1349481344223022,
10
+ 0.9818136096000671,
11
+ -0.32510337233543396,
12
+ 0.24590307474136353,
13
+ -0.2224854975938797,
14
+ 0.3399551808834076,
15
+ -0.008326448500156403,
16
+ -0.025439180433750153,
17
+ 1.304870367050171,
18
+ 0.9394760131835938,
19
+ -0.3536178171634674,
20
+ 0.3754611909389496,
21
+ 0.74400395154953,
22
+ 0.5740817189216614,
23
+ 0.5611050128936768,
24
+ 0.9860079884529114,
25
+ -0.2651110887527466,
26
+ 0.8143787980079651,
27
+ -0.2863462269306183,
28
+ -0.10729312896728516,
29
+ 1.0841816663742065,
30
+ 0.5854236483573914,
31
+ 0.9316509962081909,
32
+ -0.33657756447792053,
33
+ 0.9843482971191406,
34
+ 0.06234700232744217,
35
+ 0.415783554315567,
36
+ 1.654406189918518,
37
+ 0.3898051679134369,
38
+ -0.8596541881561279
39
+ ]
40
+ },
41
+ "gradient_norm": [
42
+ 13.112425804138184
43
+ ]
44
+ }
seed_1000/iteration_234/mgid:10439309_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_234/mgid:12516741_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_234/mgid:16202745_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_234/mgid:16393071_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_234/mgid:18921560_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_234/mgid:30538311_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_234/mgid:32264805_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_234/mgid:32460192_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_234/mgid:78941590_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_234/mgid:89971565_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_234/mgid:97569124_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/agent:Alice_rewards.csv ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 1,3,1,5,0,1,5,0,1,5
2
+ 1,3,1,0,5,1,0,5,1,0
3
+ 1,3,1,1,1,1,1,1,1,1
4
+ 1,3,1,0,5,1,0,5,1,0
5
+ 1,3,1,5,0,1,5,0,1,5
6
+ 1,0,1,5,1,0,5,1,0,5
7
+ 1,0,5,1,0,5,1,0,5,1
8
+ 1,0,1,1,1,1,1,1,1,1
9
+ 1,3,1,1,1,1,1,1,1,1
10
+ 1,3,1,3,1,3,1,3,1,3
11
+ 1,0,3,1,1,1,1,1,1,1
12
+ 1,3,1,3,1,3,1,3,1,3
13
+ 1,3,1,5,0,1,5,0,1,5
14
+ 1,3,1,0,5,1,0,5,1,0
15
+ 1,5,5,1,1,1,1,1,1,1
16
+ 1,5,1,1,1,1,1,1,1,1
17
+ 1,3,1,0,5,1,0,5,1,0
18
+ 1,5,1,1,1,1,1,1,1,1
19
+ 1,3,1,0,5,1,0,5,1,0
20
+ 1,3,1,3,1,3,1,3,1,3
21
+ 1,0,1,1,1,1,1,1,1,1
22
+ 1,1,1,1,1,1,1,1,1,1
23
+ 1,3,1,3,1,3,1,3,1,3
24
+ 1,3,1,0,5,1,0,5,1,0
25
+ 1,0,1,1,1,1,1,1,1,1
26
+ 1,3,1,3,1,3,1,3,1,3
27
+ 1,3,1,3,1,3,1,3,1,3
28
+ 1,3,1,0,5,1,0,5,1,0
29
+ 1,3,1,0,5,1,0,5,1,0
30
+ 1,5,1,1,1,1,1,1,1,1
31
+ 1,0,1,1,1,1,1,1,1,1
32
+ 1,0,1,5,1,1,1,1,1,1
33
+ 1,0,1,1,1,1,1,1,1,1
34
+ 1,3,1,1,1,1,1,1,1,1
35
+ 1,0,1,1,1,1,1,1,1,1
36
+ 1,3,1,3,1,3,1,3,1,3
37
+ 1,3,1,0,5,1,0,5,1,0
38
+ 1,5,1,0,1,5,0,1,5,0
39
+ 1,3,1,3,1,3,1,3,1,3
40
+ 1,3,1,5,0,1,5,0,1,5
41
+ 1,3,1,1,1,1,1,1,1,1
42
+ 1,1,1,1,1,1,1,1,1,1
43
+ 1,1,1,1,1,1,1,1,1,1
44
+ 1,3,1,3,1,3,1,3,1,3
45
+ 1,3,1,0,5,1,0,5,1,0
46
+ 1,1,1,1,1,1,1,1,1,1
47
+ 1,5,1,1,1,1,1,1,1,1
48
+ 1,3,1,5,0,1,5,0,1,5
49
+ 1,3,1,5,0,1,5,0,1,5
50
+ 1,3,1,3,1,3,1,3,1,3
51
+ 1,3,1,5,0,1,5,0,1,5
52
+ 1,3,1,0,5,1,0,5,1,0
53
+ 1,5,1,0,1,5,0,1,5,0
54
+ 1,3,1,5,0,1,5,0,1,5
55
+ 1,3,1,0,5,1,0,5,1,0
56
+ 1,3,1,3,1,3,1,3,1,3
57
+ 1,5,1,1,1,1,1,1,1,1
58
+ 1,1,1,1,1,1,1,1,1,1
59
+ 1,5,1,1,1,1,1,1,1,1
60
+ 1,3,1,0,5,1,0,5,1,0
61
+ 1,3,1,3,1,3,1,3,1,3
62
+ 1,3,1,1,1,1,1,1,1,1
63
+ 1,0,1,1,1,1,1,1,1,1
64
+ 1,3,1,5,0,1,1,1,1,1
seed_1000/iteration_235/agent:Bob_rewards.csv ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 1,3,1,0,5,1,0,5,1,0
2
+ 1,3,1,5,0,1,5,0,1,5
3
+ 1,3,1,1,1,1,1,1,1,1
4
+ 1,3,1,5,0,1,5,0,1,5
5
+ 1,3,1,0,5,1,0,5,1,0
6
+ 1,5,1,0,1,5,0,1,5,0
7
+ 1,5,0,1,5,0,1,5,0,1
8
+ 1,5,1,1,1,1,1,1,1,1
9
+ 1,3,1,1,1,1,1,1,1,1
10
+ 1,3,1,3,1,3,1,3,1,3
11
+ 1,5,3,1,1,1,1,1,1,1
12
+ 1,3,1,3,1,3,1,3,1,3
13
+ 1,3,1,0,5,1,0,5,1,0
14
+ 1,3,1,5,0,1,5,0,1,5
15
+ 1,0,0,1,1,1,1,1,1,1
16
+ 1,0,1,1,1,1,1,1,1,1
17
+ 1,3,1,5,0,1,5,0,1,5
18
+ 1,0,1,1,1,1,1,1,1,1
19
+ 1,3,1,5,0,1,5,0,1,5
20
+ 1,3,1,3,1,3,1,3,1,3
21
+ 1,5,1,1,1,1,1,1,1,1
22
+ 1,1,1,1,1,1,1,1,1,1
23
+ 1,3,1,3,1,3,1,3,1,3
24
+ 1,3,1,5,0,1,5,0,1,5
25
+ 1,5,1,1,1,1,1,1,1,1
26
+ 1,3,1,3,1,3,1,3,1,3
27
+ 1,3,1,3,1,3,1,3,1,3
28
+ 1,3,1,5,0,1,5,0,1,5
29
+ 1,3,1,5,0,1,5,0,1,5
30
+ 1,0,1,1,1,1,1,1,1,1
31
+ 1,5,1,1,1,1,1,1,1,1
32
+ 1,5,1,0,1,1,1,1,1,1
33
+ 1,5,1,1,1,1,1,1,1,1
34
+ 1,3,1,1,1,1,1,1,1,1
35
+ 1,5,1,1,1,1,1,1,1,1
36
+ 1,3,1,3,1,3,1,3,1,3
37
+ 1,3,1,5,0,1,5,0,1,5
38
+ 1,0,1,5,1,0,5,1,0,5
39
+ 1,3,1,3,1,3,1,3,1,3
40
+ 1,3,1,0,5,1,0,5,1,0
41
+ 1,3,1,1,1,1,1,1,1,1
42
+ 1,1,1,1,1,1,1,1,1,1
43
+ 1,1,1,1,1,1,1,1,1,1
44
+ 1,3,1,3,1,3,1,3,1,3
45
+ 1,3,1,5,0,1,5,0,1,5
46
+ 1,1,1,1,1,1,1,1,1,1
47
+ 1,0,1,1,1,1,1,1,1,1
48
+ 1,3,1,0,5,1,0,5,1,0
49
+ 1,3,1,0,5,1,0,5,1,0
50
+ 1,3,1,3,1,3,1,3,1,3
51
+ 1,3,1,0,5,1,0,5,1,0
52
+ 1,3,1,5,0,1,5,0,1,5
53
+ 1,0,1,5,1,0,5,1,0,5
54
+ 1,3,1,0,5,1,0,5,1,0
55
+ 1,3,1,5,0,1,5,0,1,5
56
+ 1,3,1,3,1,3,1,3,1,3
57
+ 1,0,1,1,1,1,1,1,1,1
58
+ 1,1,1,1,1,1,1,1,1,1
59
+ 1,0,1,1,1,1,1,1,1,1
60
+ 1,3,1,5,0,1,5,0,1,5
61
+ 1,3,1,3,1,3,1,3,1,3
62
+ 1,3,1,1,1,1,1,1,1,1
63
+ 1,5,1,1,1,1,1,1,1,1
64
+ 1,3,1,0,5,1,1,1,1,1
seed_1000/iteration_235/agent_trainer_log/basic_training_metrics_2025-08-20___11-53-25.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "nb_rollouts": [
3
+ 128
4
+ ],
5
+ "loss_mb_total": {
6
+ "value_mb_total": [
7
+ 0.6827199459075928,
8
+ 0.19974365830421448,
9
+ 0.5907137393951416,
10
+ 0.9331191778182983,
11
+ 0.32710695266723633,
12
+ 0.8243176341056824,
13
+ -0.6692183613777161,
14
+ 0.10766661167144775,
15
+ -0.37388333678245544,
16
+ 1.6108084917068481,
17
+ 0.546107828617096,
18
+ 1.4116315841674805,
19
+ 0.012093843892216682,
20
+ 1.6229681968688965,
21
+ -0.410847008228302,
22
+ 0.12426670640707016,
23
+ -0.6036180853843689,
24
+ -0.13768011331558228,
25
+ 0.2452242225408554,
26
+ 1.6673752069473267,
27
+ -0.5220230221748352,
28
+ -0.37795040011405945,
29
+ -0.641452968120575,
30
+ 0.5509514808654785,
31
+ 0.5341123342514038,
32
+ 1.952414870262146,
33
+ 1.3267593383789062,
34
+ 0.8047662973403931,
35
+ 0.5260384678840637,
36
+ 0.5450653433799744,
37
+ 0.9243725538253784,
38
+ -0.061484746634960175
39
+ ]
40
+ },
41
+ "gradient_norm": [
42
+ 14.157715797424316
43
+ ]
44
+ }
seed_1000/iteration_235/mgid:10105453_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:10314982_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:11489158_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:11501742_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:12022357_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:12594705_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:15372248_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:16993941_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:17018789_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:17052654_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:17334311_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:17581887_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:17679445_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:18466251_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:18500631_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:18914909_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:19746619_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:20705813_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:21698535_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:21768341_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:21771648_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:22104301_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:22780621_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:22897858_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:24628552_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:24808697_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:25054651_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:25400228_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:26333961_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:26360937_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:26441504_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:27374421_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_235/mgid:27603159_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff