Muqeeth commited on
Commit
6b2830d
·
verified ·
1 Parent(s): 40c5031

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_019/mgid:85308280_rollout_tree.json +0 -0
  2. seed_1000/iteration_023/agent:Alice_rewards.csv +64 -0
  3. seed_1000/iteration_023/agent:Bob_rewards.csv +64 -0
  4. seed_1000/iteration_023/agent_trainer_log/basic_training_metrics_2025-08-20___08-34-56.json +44 -0
  5. seed_1000/iteration_023/mgid:10280976_rollout_tree.json +0 -0
  6. seed_1000/iteration_023/mgid:17313327_rollout_tree.json +0 -0
  7. seed_1000/iteration_023/mgid:18163115_rollout_tree.json +0 -0
  8. seed_1000/iteration_023/mgid:19636206_rollout_tree.json +0 -0
  9. seed_1000/iteration_023/mgid:19711271_rollout_tree.json +0 -0
  10. seed_1000/iteration_023/mgid:21516746_rollout_tree.json +0 -0
  11. seed_1000/iteration_023/mgid:22376753_rollout_tree.json +0 -0
  12. seed_1000/iteration_023/mgid:25159833_rollout_tree.json +0 -0
  13. seed_1000/iteration_023/mgid:25514523_rollout_tree.json +0 -0
  14. seed_1000/iteration_023/mgid:28378528_rollout_tree.json +0 -0
  15. seed_1000/iteration_023/mgid:29866938_rollout_tree.json +0 -0
  16. seed_1000/iteration_023/mgid:31189624_rollout_tree.json +0 -0
  17. seed_1000/iteration_023/mgid:69197156_rollout_tree.json +0 -0
  18. seed_1000/iteration_023/mgid:83633304_rollout_tree.json +0 -0
  19. seed_1000/iteration_024/agent:Alice_rewards.csv +64 -0
  20. seed_1000/iteration_024/agent:Bob_rewards.csv +64 -0
  21. seed_1000/iteration_024/agent_trainer_log/basic_training_metrics_2025-08-20___08-35-52.json +44 -0
  22. seed_1000/iteration_024/mgid:10482499_rollout_tree.json +0 -0
  23. seed_1000/iteration_024/mgid:11352426_rollout_tree.json +0 -0
  24. seed_1000/iteration_024/mgid:11493960_rollout_tree.json +0 -0
  25. seed_1000/iteration_024/mgid:11542789_rollout_tree.json +0 -0
  26. seed_1000/iteration_024/mgid:11699694_rollout_tree.json +0 -0
  27. seed_1000/iteration_024/mgid:12592592_rollout_tree.json +0 -0
  28. seed_1000/iteration_024/mgid:13201698_rollout_tree.json +0 -0
  29. seed_1000/iteration_024/mgid:14249411_rollout_tree.json +0 -0
  30. seed_1000/iteration_024/mgid:14283261_rollout_tree.json +0 -0
  31. seed_1000/iteration_024/mgid:14520558_rollout_tree.json +0 -0
  32. seed_1000/iteration_024/mgid:14563655_rollout_tree.json +0 -0
  33. seed_1000/iteration_024/mgid:14680479_rollout_tree.json +0 -0
  34. seed_1000/iteration_024/mgid:15210030_rollout_tree.json +0 -0
  35. seed_1000/iteration_024/mgid:15295871_rollout_tree.json +0 -0
  36. seed_1000/iteration_024/mgid:15681311_rollout_tree.json +0 -0
  37. seed_1000/iteration_024/mgid:16386479_rollout_tree.json +0 -0
  38. seed_1000/iteration_024/mgid:16536092_rollout_tree.json +0 -0
  39. seed_1000/iteration_024/mgid:16864754_rollout_tree.json +0 -0
  40. seed_1000/iteration_024/mgid:17051604_rollout_tree.json +0 -0
  41. seed_1000/iteration_024/mgid:17609044_rollout_tree.json +0 -0
  42. seed_1000/iteration_024/mgid:18127640_rollout_tree.json +0 -0
  43. seed_1000/iteration_024/mgid:18575783_rollout_tree.json +0 -0
  44. seed_1000/iteration_024/mgid:20692053_rollout_tree.json +0 -0
  45. seed_1000/iteration_024/mgid:20721370_rollout_tree.json +0 -0
  46. seed_1000/iteration_024/mgid:21656275_rollout_tree.json +0 -0
  47. seed_1000/iteration_024/mgid:21744703_rollout_tree.json +0 -0
  48. seed_1000/iteration_024/mgid:23588383_rollout_tree.json +0 -0
  49. seed_1000/iteration_024/mgid:24049181_rollout_tree.json +0 -0
  50. seed_1000/iteration_024/mgid:24420045_rollout_tree.json +0 -0
seed_1000/iteration_019/mgid:85308280_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_023/agent:Alice_rewards.csv ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 1,3,1,3,1,3,1,3,1,3
2
+ 1,3,1,3,1,3,1,3,1,3
3
+ 1,5,1,5,1,5,1,5,1,5
4
+ 1,0,5,1,0,5,1,0,5,1
5
+ 1,3,1,3,1,3,1,3,1,3
6
+ 1,3,1,3,1,3,1,3,1,3
7
+ 1,3,1,3,1,3,1,3,1,3
8
+ 1,3,1,5,1,3,1,3,1,3
9
+ 1,3,1,3,1,3,1,3,1,3
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
+ 1,0,1,0,1,0,1,0,1,0
14
+ 1,3,1,3,1,3,1,3,1,3
15
+ 1,0,1,1,1,1,1,1,1,1
16
+ 1,3,1,3,1,3,1,3,1,3
17
+ 1,3,1,3,1,3,1,3,1,3
18
+ 1,3,1,3,1,3,1,3,1,3
19
+ 1,0,1,0,1,0,1,0,1,0
20
+ 1,3,1,3,1,3,1,3,1,3
21
+ 1,3,1,3,1,3,1,3,1,3
22
+ 1,3,1,3,1,3,1,3,1,3
23
+ 1,3,1,3,1,3,1,3,1,3
24
+ 1,3,1,3,1,3,1,3,1,3
25
+ 1,1,1,1,1,1,1,1,1,1
26
+ 1,3,1,3,1,3,1,3,1,3
27
+ 1,3,1,3,1,3,1,3,1,3
28
+ 1,0,1,0,1,0,1,0,1,0
29
+ 1,3,1,3,1,3,1,3,1,3
30
+ 1,3,1,3,1,3,1,3,1,3
31
+ 1,5,1,5,1,5,1,5,1,5
32
+ 1,3,1,3,1,3,1,3,1,3
33
+ 1,5,1,5,1,5,1,5,1,5
34
+ 1,3,1,3,1,3,1,3,1,3
35
+ 1,5,1,5,1,5,1,5,1,5
36
+ 1,3,1,3,1,3,1,3,1,3
37
+ 1,3,1,3,1,3,1,3,1,3
38
+ 1,3,1,3,1,3,1,3,1,3
39
+ 1,0,5,1,0,5,1,0,5,1
40
+ 1,1,1,1,1,1,1,1,1,1
41
+ 1,1,1,1,1,1,1,1,1,1
42
+ 1,3,1,3,1,3,1,3,1,3
43
+ 1,3,1,3,1,3,1,3,1,3
44
+ 1,5,1,1,1,1,1,1,1,1
45
+ 1,3,1,3,1,3,1,3,1,3
46
+ 1,1,1,1,1,1,1,1,1,1
47
+ 1,3,1,3,1,3,1,3,1,3
48
+ 1,5,5,1,1,1,1,1,1,1
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
+ 1,0,0,1,1,1,1,1,1,1
54
+ 1,3,1,3,1,3,1,3,1,3
55
+ 1,5,1,1,1,1,1,1,1,1
56
+ 1,5,1,1,1,1,1,1,1,1
57
+ 1,0,1,0,1,0,1,0,1,0
58
+ 1,0,1,0,1,0,1,0,1,0
59
+ 1,0,5,1,0,5,1,0,5,1
60
+ 1,3,1,3,1,3,1,3,1,3
61
+ 1,5,1,5,1,5,1,5,1,5
62
+ 1,3,1,3,1,3,1,3,1,3
63
+ 1,3,1,3,1,3,1,3,1,3
64
+ 1,0,5,1,0,5,1,0,5,1
seed_1000/iteration_023/agent:Bob_rewards.csv ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 1,3,1,3,1,3,1,3,1,3
2
+ 1,3,1,3,1,3,1,3,1,3
3
+ 1,0,1,0,1,0,1,0,1,0
4
+ 1,5,0,1,5,0,1,5,0,1
5
+ 1,3,1,3,1,3,1,3,1,3
6
+ 1,3,1,3,1,3,1,3,1,3
7
+ 1,3,1,3,1,3,1,3,1,3
8
+ 1,3,1,0,1,3,1,3,1,3
9
+ 1,3,1,3,1,3,1,3,1,3
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
+ 1,5,1,5,1,5,1,5,1,5
14
+ 1,3,1,3,1,3,1,3,1,3
15
+ 1,5,1,1,1,1,1,1,1,1
16
+ 1,3,1,3,1,3,1,3,1,3
17
+ 1,3,1,3,1,3,1,3,1,3
18
+ 1,3,1,3,1,3,1,3,1,3
19
+ 1,5,1,5,1,5,1,5,1,5
20
+ 1,3,1,3,1,3,1,3,1,3
21
+ 1,3,1,3,1,3,1,3,1,3
22
+ 1,3,1,3,1,3,1,3,1,3
23
+ 1,3,1,3,1,3,1,3,1,3
24
+ 1,3,1,3,1,3,1,3,1,3
25
+ 1,1,1,1,1,1,1,1,1,1
26
+ 1,3,1,3,1,3,1,3,1,3
27
+ 1,3,1,3,1,3,1,3,1,3
28
+ 1,5,1,5,1,5,1,5,1,5
29
+ 1,3,1,3,1,3,1,3,1,3
30
+ 1,3,1,3,1,3,1,3,1,3
31
+ 1,0,1,0,1,0,1,0,1,0
32
+ 1,3,1,3,1,3,1,3,1,3
33
+ 1,0,1,0,1,0,1,0,1,0
34
+ 1,3,1,3,1,3,1,3,1,3
35
+ 1,0,1,0,1,0,1,0,1,0
36
+ 1,3,1,3,1,3,1,3,1,3
37
+ 1,3,1,3,1,3,1,3,1,3
38
+ 1,3,1,3,1,3,1,3,1,3
39
+ 1,5,0,1,5,0,1,5,0,1
40
+ 1,1,1,1,1,1,1,1,1,1
41
+ 1,1,1,1,1,1,1,1,1,1
42
+ 1,3,1,3,1,3,1,3,1,3
43
+ 1,3,1,3,1,3,1,3,1,3
44
+ 1,0,1,1,1,1,1,1,1,1
45
+ 1,3,1,3,1,3,1,3,1,3
46
+ 1,1,1,1,1,1,1,1,1,1
47
+ 1,3,1,3,1,3,1,3,1,3
48
+ 1,0,0,1,1,1,1,1,1,1
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
+ 1,5,5,1,1,1,1,1,1,1
54
+ 1,3,1,3,1,3,1,3,1,3
55
+ 1,0,1,1,1,1,1,1,1,1
56
+ 1,0,1,1,1,1,1,1,1,1
57
+ 1,5,1,5,1,5,1,5,1,5
58
+ 1,5,1,5,1,5,1,5,1,5
59
+ 1,5,0,1,5,0,1,5,0,1
60
+ 1,3,1,3,1,3,1,3,1,3
61
+ 1,0,1,0,1,0,1,0,1,0
62
+ 1,3,1,3,1,3,1,3,1,3
63
+ 1,3,1,3,1,3,1,3,1,3
64
+ 1,5,0,1,5,0,1,5,0,1
seed_1000/iteration_023/agent_trainer_log/basic_training_metrics_2025-08-20___08-34-56.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "nb_rollouts": [
3
+ 128
4
+ ],
5
+ "loss_mb_total": {
6
+ "value_mb_total": [
7
+ 1.4616807699203491,
8
+ 1.0306288003921509,
9
+ 0.3218361735343933,
10
+ 1.3617950677871704,
11
+ -3.958965301513672,
12
+ -1.1660590171813965,
13
+ 1.4616807699203491,
14
+ 0.7446512579917908,
15
+ 0.14781084656715393,
16
+ -5.033266544342041,
17
+ -0.0917583703994751,
18
+ 0.724884033203125,
19
+ -4.216623783111572,
20
+ -1.224156379699707,
21
+ -3.7193965911865234,
22
+ -4.64767599105835,
23
+ 1.6263912916183472,
24
+ 0.5052778720855713,
25
+ 1.1760354042053223,
26
+ -0.29731330275535583,
27
+ -0.04928698018193245,
28
+ -8.564029693603516,
29
+ 1.6263912916183472,
30
+ -0.7527523040771484,
31
+ -3.4688189029693604,
32
+ -4.902184963226318,
33
+ -3.7111310958862305,
34
+ 0.8859889507293701,
35
+ -0.3050648272037506,
36
+ 0.5968314409255981,
37
+ 0.19302526116371155,
38
+ -1.426178216934204
39
+ ]
40
+ },
41
+ "gradient_norm": [
42
+ 25.44721794128418
43
+ ]
44
+ }
seed_1000/iteration_023/mgid:10280976_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_023/mgid:17313327_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_023/mgid:18163115_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_023/mgid:19636206_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_023/mgid:19711271_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_023/mgid:21516746_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_023/mgid:22376753_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_023/mgid:25159833_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_023/mgid:25514523_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_023/mgid:28378528_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_023/mgid:29866938_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_023/mgid:31189624_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_023/mgid:69197156_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_023/mgid:83633304_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/agent:Alice_rewards.csv ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 1,5,0,1,5,0,1,5,0,1
2
+ 1,3,1,3,1,3,1,3,1,3
3
+ 1,3,1,3,1,3,1,3,1,3
4
+ 1,3,1,3,1,3,1,3,1,3
5
+ 1,3,1,3,1,3,1,3,1,3
6
+ 1,5,1,5,1,5,1,5,1,5
7
+ 1,3,1,3,1,3,1,3,1,3
8
+ 1,5,1,5,1,5,1,5,1,5
9
+ 1,5,1,5,1,5,1,5,1,5
10
+ 1,3,1,3,1,3,1,3,1,3
11
+ 1,0,1,0,1,0,1,0,1,0
12
+ 1,3,1,3,1,3,1,3,1,3
13
+ 1,3,1,3,1,3,1,3,1,3
14
+ 1,0,1,0,1,0,1,0,1,0
15
+ 1,0,5,1,0,5,1,0,5,1
16
+ 1,3,1,3,1,3,1,3,1,3
17
+ 1,5,0,1,5,0,1,5,0,1
18
+ 1,5,1,5,1,5,1,5,1,5
19
+ 1,0,1,0,1,0,1,0,1,0
20
+ 1,3,1,3,1,3,1,3,1,3
21
+ 1,0,5,1,0,5,1,0,5,1
22
+ 1,0,1,0,1,0,1,0,1,0
23
+ 1,3,1,3,1,3,1,3,1,3
24
+ 1,3,1,3,1,3,1,3,1,3
25
+ 1,0,5,1,0,5,1,0,5,1
26
+ 1,3,1,3,1,3,1,3,1,3
27
+ 1,3,1,3,1,3,1,3,1,3
28
+ 1,3,1,3,1,3,1,3,1,3
29
+ 1,3,1,3,1,3,1,3,1,3
30
+ 1,3,1,3,1,3,1,3,1,3
31
+ 1,3,1,5,0,1,5,0,1,5
32
+ 1,5,1,5,1,5,1,5,1,5
33
+ 1,3,1,3,1,3,1,3,1,3
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
+ 1,0,1,0,1,0,1,0,1,0
39
+ 1,3,1,3,1,3,1,3,1,3
40
+ 1,3,1,3,1,3,1,3,1,3
41
+ 1,3,1,3,1,3,1,3,1,3
42
+ 1,5,3,1,1,1,1,1,1,1
43
+ 1,3,1,3,1,3,1,3,1,3
44
+ 1,0,1,0,1,0,1,0,1,0
45
+ 1,3,1,3,1,3,1,3,1,3
46
+ 1,5,1,5,1,5,1,5,1,5
47
+ 1,5,0,1,5,0,1,5,0,1
48
+ 1,0,5,1,0,5,1,0,5,1
49
+ 1,3,1,3,1,3,1,3,1,3
50
+ 1,0,5,1,0,5,1,0,5,1
51
+ 1,3,1,3,1,3,1,3,1,3
52
+ 1,5,1,5,1,5,1,5,1,5
53
+ 1,3,1,3,1,3,1,3,1,3
54
+ 1,0,1,1,1,1,1,1,1,1
55
+ 1,3,1,3,1,3,1,3,1,3
56
+ 1,0,5,1,0,5,1,0,5,1
57
+ 1,3,1,3,1,3,1,3,1,3
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
+ 1,0,1,0,1,0,1,0,1,0
62
+ 1,1,1,1,1,1,1,1,1,1
63
+ 1,3,1,3,1,3,1,3,1,3
64
+ 1,5,0,1,5,0,1,5,0,1
seed_1000/iteration_024/agent:Bob_rewards.csv ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 1,0,5,1,0,5,1,0,5,1
2
+ 1,3,1,3,1,3,1,3,1,3
3
+ 1,3,1,3,1,3,1,3,1,3
4
+ 1,3,1,3,1,3,1,3,1,3
5
+ 1,3,1,3,1,3,1,3,1,3
6
+ 1,0,1,0,1,0,1,0,1,0
7
+ 1,3,1,3,1,3,1,3,1,3
8
+ 1,0,1,0,1,0,1,0,1,0
9
+ 1,0,1,0,1,0,1,0,1,0
10
+ 1,3,1,3,1,3,1,3,1,3
11
+ 1,5,1,5,1,5,1,5,1,5
12
+ 1,3,1,3,1,3,1,3,1,3
13
+ 1,3,1,3,1,3,1,3,1,3
14
+ 1,5,1,5,1,5,1,5,1,5
15
+ 1,5,0,1,5,0,1,5,0,1
16
+ 1,3,1,3,1,3,1,3,1,3
17
+ 1,0,5,1,0,5,1,0,5,1
18
+ 1,0,1,0,1,0,1,0,1,0
19
+ 1,5,1,5,1,5,1,5,1,5
20
+ 1,3,1,3,1,3,1,3,1,3
21
+ 1,5,0,1,5,0,1,5,0,1
22
+ 1,5,1,5,1,5,1,5,1,5
23
+ 1,3,1,3,1,3,1,3,1,3
24
+ 1,3,1,3,1,3,1,3,1,3
25
+ 1,5,0,1,5,0,1,5,0,1
26
+ 1,3,1,3,1,3,1,3,1,3
27
+ 1,3,1,3,1,3,1,3,1,3
28
+ 1,3,1,3,1,3,1,3,1,3
29
+ 1,3,1,3,1,3,1,3,1,3
30
+ 1,3,1,3,1,3,1,3,1,3
31
+ 1,3,1,0,5,1,0,5,1,0
32
+ 1,0,1,0,1,0,1,0,1,0
33
+ 1,3,1,3,1,3,1,3,1,3
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
+ 1,5,1,5,1,5,1,5,1,5
39
+ 1,3,1,3,1,3,1,3,1,3
40
+ 1,3,1,3,1,3,1,3,1,3
41
+ 1,3,1,3,1,3,1,3,1,3
42
+ 1,0,3,1,1,1,1,1,1,1
43
+ 1,3,1,3,1,3,1,3,1,3
44
+ 1,5,1,5,1,5,1,5,1,5
45
+ 1,3,1,3,1,3,1,3,1,3
46
+ 1,0,1,0,1,0,1,0,1,0
47
+ 1,0,5,1,0,5,1,0,5,1
48
+ 1,5,0,1,5,0,1,5,0,1
49
+ 1,3,1,3,1,3,1,3,1,3
50
+ 1,5,0,1,5,0,1,5,0,1
51
+ 1,3,1,3,1,3,1,3,1,3
52
+ 1,0,1,0,1,0,1,0,1,0
53
+ 1,3,1,3,1,3,1,3,1,3
54
+ 1,5,1,1,1,1,1,1,1,1
55
+ 1,3,1,3,1,3,1,3,1,3
56
+ 1,5,0,1,5,0,1,5,0,1
57
+ 1,3,1,3,1,3,1,3,1,3
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
+ 1,5,1,5,1,5,1,5,1,5
62
+ 1,1,1,1,1,1,1,1,1,1
63
+ 1,3,1,3,1,3,1,3,1,3
64
+ 1,0,5,1,0,5,1,0,5,1
seed_1000/iteration_024/agent_trainer_log/basic_training_metrics_2025-08-20___08-35-52.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "nb_rollouts": [
3
+ 128
4
+ ],
5
+ "loss_mb_total": {
6
+ "value_mb_total": [
7
+ 1.0253727436065674,
8
+ -0.8116970658302307,
9
+ -4.214677810668945,
10
+ -5.77639627456665,
11
+ -0.7579552531242371,
12
+ -0.5945085883140564,
13
+ 0.5865748524665833,
14
+ -5.758964538574219,
15
+ 0.8037633895874023,
16
+ -5.612949848175049,
17
+ -4.378124237060547,
18
+ 0.48991426825523376,
19
+ -5.93984317779541,
20
+ 0.36938634514808655,
21
+ -5.2502851486206055,
22
+ 0.8037633895874023,
23
+ 0.305438369512558,
24
+ -4.313109397888184,
25
+ -0.5951905250549316,
26
+ -5.790152549743652,
27
+ -4.349602222442627,
28
+ -4.145242691040039,
29
+ 0.677493155002594,
30
+ -5.723854064941406,
31
+ 0.8453600406646729,
32
+ -5.585793495178223,
33
+ -0.7995495796203613,
34
+ -0.17409297823905945,
35
+ -5.99451208114624,
36
+ 0.5096263885498047,
37
+ -0.9942831993103027,
38
+ 0.8453600406646729
39
+ ]
40
+ },
41
+ "gradient_norm": [
42
+ 54.52265548706055
43
+ ]
44
+ }
seed_1000/iteration_024/mgid:10482499_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:11352426_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:11493960_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:11542789_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:11699694_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:12592592_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:13201698_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:14249411_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:14283261_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:14520558_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:14563655_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:14680479_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:15210030_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:15295871_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:15681311_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:16386479_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:16536092_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:16864754_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:17051604_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:17609044_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:18127640_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:18575783_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:20692053_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:20721370_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:21656275_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:21744703_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:23588383_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:24049181_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_024/mgid:24420045_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff