fastwalker1118 commited on
Commit
6070718
·
verified ·
1 Parent(s): b7679bf

Add task-5 evaluation videos and per-instance results

Browse files
Files changed (45) hide show
  1. .gitattributes +40 -0
  2. task5/eval_videos/README.md +49 -0
  3. task5/eval_videos/merged15000/results.json +188 -0
  4. task5/eval_videos/merged20000/inst301_idx00_q0.6667.mp4 +3 -0
  5. task5/eval_videos/merged20000/inst302_idx01_q0.5000.mp4 +3 -0
  6. task5/eval_videos/merged20000/inst303_idx02_q0.6667.mp4 +3 -0
  7. task5/eval_videos/merged20000/inst304_idx03_q0.6667.mp4 +3 -0
  8. task5/eval_videos/merged20000/inst305_idx04_q0.6667.mp4 +3 -0
  9. task5/eval_videos/merged20000/inst306_idx05_q0.6667.mp4 +3 -0
  10. task5/eval_videos/merged20000/inst307_idx06_q0.3333.mp4 +3 -0
  11. task5/eval_videos/merged20000/inst308_idx07_q0.6667.mp4 +3 -0
  12. task5/eval_videos/merged20000/inst309_idx08_q0.6667.mp4 +3 -0
  13. task5/eval_videos/merged20000/inst310_idx09_q0.6667.mp4 +3 -0
  14. task5/eval_videos/merged20000/inst311_idx10_q0.1667.mp4 +3 -0
  15. task5/eval_videos/merged20000/inst312_idx11_q0.6667.mp4 +3 -0
  16. task5/eval_videos/merged20000/inst313_idx12_q0.3333.mp4 +3 -0
  17. task5/eval_videos/merged20000/inst314_idx13_q0.6667.mp4 +3 -0
  18. task5/eval_videos/merged20000/inst315_idx14_q0.8333.mp4 +3 -0
  19. task5/eval_videos/merged20000/inst316_idx15_q0.6667.mp4 +3 -0
  20. task5/eval_videos/merged20000/inst317_idx16_q0.6667.mp4 +3 -0
  21. task5/eval_videos/merged20000/inst318_idx17_q0.6667.mp4 +3 -0
  22. task5/eval_videos/merged20000/inst319_idx18_q0.8333.mp4 +3 -0
  23. task5/eval_videos/merged20000/inst320_idx19_q0.6667.mp4 +3 -0
  24. task5/eval_videos/merged20000/results.json +188 -0
  25. task5/eval_videos/merged39999/inst301_idx00_q0.6667.mp4 +3 -0
  26. task5/eval_videos/merged39999/inst302_idx01_q1.0000.mp4 +3 -0
  27. task5/eval_videos/merged39999/inst303_idx02_q0.6667.mp4 +3 -0
  28. task5/eval_videos/merged39999/inst304_idx03_q0.8333.mp4 +3 -0
  29. task5/eval_videos/merged39999/inst305_idx04_q0.6667.mp4 +3 -0
  30. task5/eval_videos/merged39999/inst306_idx05_q0.6667.mp4 +3 -0
  31. task5/eval_videos/merged39999/inst307_idx06_q0.6667.mp4 +3 -0
  32. task5/eval_videos/merged39999/inst308_idx07_q0.6667.mp4 +3 -0
  33. task5/eval_videos/merged39999/inst309_idx08_q0.6667.mp4 +3 -0
  34. task5/eval_videos/merged39999/inst310_idx09_q0.3333.mp4 +3 -0
  35. task5/eval_videos/merged39999/inst311_idx10_q0.6667.mp4 +3 -0
  36. task5/eval_videos/merged39999/inst312_idx11_q0.6667.mp4 +3 -0
  37. task5/eval_videos/merged39999/inst313_idx12_q0.6667.mp4 +3 -0
  38. task5/eval_videos/merged39999/inst314_idx13_q0.5000.mp4 +3 -0
  39. task5/eval_videos/merged39999/inst315_idx14_q0.6667.mp4 +3 -0
  40. task5/eval_videos/merged39999/inst316_idx15_q0.6667.mp4 +3 -0
  41. task5/eval_videos/merged39999/inst317_idx16_q0.1667.mp4 +3 -0
  42. task5/eval_videos/merged39999/inst318_idx17_q0.6667.mp4 +3 -0
  43. task5/eval_videos/merged39999/inst319_idx18_q0.6667.mp4 +3 -0
  44. task5/eval_videos/merged39999/inst320_idx19_q0.6667.mp4 +3 -0
  45. task5/eval_videos/merged39999/results.json +188 -0
.gitattributes CHANGED
@@ -305,3 +305,43 @@ task5/task5ckptmerged35000/params/ocdbt.process_0/d/c301cf781aa30e68bbcd9caf90f4
305
  task5/task5ckptmerged35000/params/ocdbt.process_0/d/caa2b4579140b90cf7f66b2d1ee51928 filter=lfs diff=lfs merge=lfs -text
306
  task5/task5ckptmerged35000/params/ocdbt.process_0/d/de57e34ff8d363e5676aada6ee750f7a filter=lfs diff=lfs merge=lfs -text
307
  task5/task5ckptmerged35000/params/ocdbt.process_0/d/f916eefba10b5d88c618466e0664bccc filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
305
  task5/task5ckptmerged35000/params/ocdbt.process_0/d/caa2b4579140b90cf7f66b2d1ee51928 filter=lfs diff=lfs merge=lfs -text
306
  task5/task5ckptmerged35000/params/ocdbt.process_0/d/de57e34ff8d363e5676aada6ee750f7a filter=lfs diff=lfs merge=lfs -text
307
  task5/task5ckptmerged35000/params/ocdbt.process_0/d/f916eefba10b5d88c618466e0664bccc filter=lfs diff=lfs merge=lfs -text
308
+ task5/eval_videos/merged20000/inst301_idx00_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
309
+ task5/eval_videos/merged20000/inst302_idx01_q0.5000.mp4 filter=lfs diff=lfs merge=lfs -text
310
+ task5/eval_videos/merged20000/inst303_idx02_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
311
+ task5/eval_videos/merged20000/inst304_idx03_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
312
+ task5/eval_videos/merged20000/inst305_idx04_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
313
+ task5/eval_videos/merged20000/inst306_idx05_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
314
+ task5/eval_videos/merged20000/inst307_idx06_q0.3333.mp4 filter=lfs diff=lfs merge=lfs -text
315
+ task5/eval_videos/merged20000/inst308_idx07_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
316
+ task5/eval_videos/merged20000/inst309_idx08_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
317
+ task5/eval_videos/merged20000/inst310_idx09_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
318
+ task5/eval_videos/merged20000/inst311_idx10_q0.1667.mp4 filter=lfs diff=lfs merge=lfs -text
319
+ task5/eval_videos/merged20000/inst312_idx11_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
320
+ task5/eval_videos/merged20000/inst313_idx12_q0.3333.mp4 filter=lfs diff=lfs merge=lfs -text
321
+ task5/eval_videos/merged20000/inst314_idx13_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
322
+ task5/eval_videos/merged20000/inst315_idx14_q0.8333.mp4 filter=lfs diff=lfs merge=lfs -text
323
+ task5/eval_videos/merged20000/inst316_idx15_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
324
+ task5/eval_videos/merged20000/inst317_idx16_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
325
+ task5/eval_videos/merged20000/inst318_idx17_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
326
+ task5/eval_videos/merged20000/inst319_idx18_q0.8333.mp4 filter=lfs diff=lfs merge=lfs -text
327
+ task5/eval_videos/merged20000/inst320_idx19_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
328
+ task5/eval_videos/merged39999/inst301_idx00_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
329
+ task5/eval_videos/merged39999/inst302_idx01_q1.0000.mp4 filter=lfs diff=lfs merge=lfs -text
330
+ task5/eval_videos/merged39999/inst303_idx02_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
331
+ task5/eval_videos/merged39999/inst304_idx03_q0.8333.mp4 filter=lfs diff=lfs merge=lfs -text
332
+ task5/eval_videos/merged39999/inst305_idx04_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
333
+ task5/eval_videos/merged39999/inst306_idx05_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
334
+ task5/eval_videos/merged39999/inst307_idx06_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
335
+ task5/eval_videos/merged39999/inst308_idx07_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
336
+ task5/eval_videos/merged39999/inst309_idx08_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
337
+ task5/eval_videos/merged39999/inst310_idx09_q0.3333.mp4 filter=lfs diff=lfs merge=lfs -text
338
+ task5/eval_videos/merged39999/inst311_idx10_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
339
+ task5/eval_videos/merged39999/inst312_idx11_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
340
+ task5/eval_videos/merged39999/inst313_idx12_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
341
+ task5/eval_videos/merged39999/inst314_idx13_q0.5000.mp4 filter=lfs diff=lfs merge=lfs -text
342
+ task5/eval_videos/merged39999/inst315_idx14_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
343
+ task5/eval_videos/merged39999/inst316_idx15_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
344
+ task5/eval_videos/merged39999/inst317_idx16_q0.1667.mp4 filter=lfs diff=lfs merge=lfs -text
345
+ task5/eval_videos/merged39999/inst318_idx17_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
346
+ task5/eval_videos/merged39999/inst319_idx18_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
347
+ task5/eval_videos/merged39999/inst320_idx19_q0.6667.mp4 filter=lfs diff=lfs merge=lfs -text
task5/eval_videos/README.md ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # task-5 `setting_mousetraps` — evaluation videos
2
+
3
+ Rollout videos and per-instance scores from the stock BEHAVIOR v3.9.1 evaluator
4
+ (`omnigibson.eval.eval`, commit `9a03ca3f`), non-fast path, on the 20 official
5
+ `public_test` instances (ids 301–320).
6
+
7
+ ## Layout
8
+
9
+ ```
10
+ merged39999/ 20 videos + results.json mean q 0.6417 success 1/20
11
+ merged20000/ 20 videos + results.json mean q 0.6167 success 0/20
12
+ merged15000/ results.json only mean q 0.6250 success 2/20
13
+ ```
14
+
15
+ Filenames encode the outcome: `inst<id>_idx<NN>_q<score>.mp4`.
16
+ Each video is h264 672x448 — head plus both wrist cameras tiled into one frame.
17
+ `merged15000` has no videos because that sweep predated `--write-video`.
18
+
19
+ ## Eval configuration
20
+
21
+ Two settings differ from a stock submission run and both matter when reading these numbers:
22
+
23
+ - **`B1K_STATE_2026=1`** — the 61-dim `PROP_2026` state extraction. Without it the
24
+ 2025 extractor's slices (`base_qvel` 253:256) run off the end of v3.9.x's 61-dim
25
+ proprioception and silently yield a 2-element state, so the policy receives a
26
+ constant input and scores 0. This flag is required, not optional.
27
+ - **correction rules disabled** (`--no-apply-eval-tricks`) — they index `state[14]`
28
+ and raise `IndexError` on the collapsed state; disabling them was the only way to
29
+ complete rollouts while diagnosing. Re-enabling is untested.
30
+
31
+ Also applied: 100-task / 1120-stage embedding tables, which these checkpoints
32
+ require and the 50-task solution repos do not provide.
33
+
34
+ ## What the scores say
35
+
36
+ ```
37
+ merged15000 0.6250 merged20000 0.6167 merged39999 0.6417
38
+ ```
39
+
40
+ A 0.025 spread across 15k–40k training steps, identical medians (0.6667), and a
41
+ paired sign test of 39999 vs 15000 giving p = 0.754. There is no evidence these
42
+ checkpoints differ; training further did not help.
43
+
44
+ The consistent feature is a ceiling: **14 of 20 instances score exactly 0.6667**
45
+ and 19 of 20 run to the 15,295-step cap. `q_score` counts goal predicates that
46
+ flipped false→true divided by the total in that option, so a predicate already
47
+ true at reset counts in the denominator but can never earn credit. Whether the
48
+ 0.6667 wall is an unachieved condition or an uncreditable pre-satisfied one is
49
+ not resolved by these files.
task5/eval_videos/merged15000/results.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint": "merged15000",
3
+ "n_instances": 20,
4
+ "mean_q": 0.625,
5
+ "success": 2,
6
+ "episodes": [
7
+ {
8
+ "idx": 0,
9
+ "instance_id": 301,
10
+ "q_score": 1.0,
11
+ "success": true,
12
+ "steps": 11427,
13
+ "base_distance_m": 7.83,
14
+ "video": null
15
+ },
16
+ {
17
+ "idx": 1,
18
+ "instance_id": 302,
19
+ "q_score": 0.6666666666666666,
20
+ "success": false,
21
+ "steps": 15295,
22
+ "base_distance_m": 7.47,
23
+ "video": null
24
+ },
25
+ {
26
+ "idx": 2,
27
+ "instance_id": 303,
28
+ "q_score": 0.5,
29
+ "success": false,
30
+ "steps": 15295,
31
+ "base_distance_m": 9.96,
32
+ "video": null
33
+ },
34
+ {
35
+ "idx": 3,
36
+ "instance_id": 304,
37
+ "q_score": 0.5,
38
+ "success": false,
39
+ "steps": 15295,
40
+ "base_distance_m": 12.02,
41
+ "video": null
42
+ },
43
+ {
44
+ "idx": 4,
45
+ "instance_id": 305,
46
+ "q_score": 0.6666666666666666,
47
+ "success": false,
48
+ "steps": 15295,
49
+ "base_distance_m": 15.44,
50
+ "video": null
51
+ },
52
+ {
53
+ "idx": 5,
54
+ "instance_id": 306,
55
+ "q_score": 0.6666666666666666,
56
+ "success": false,
57
+ "steps": 15295,
58
+ "base_distance_m": 11.72,
59
+ "video": null
60
+ },
61
+ {
62
+ "idx": 6,
63
+ "instance_id": 307,
64
+ "q_score": 0.6666666666666666,
65
+ "success": false,
66
+ "steps": 15295,
67
+ "base_distance_m": 10.32,
68
+ "video": null
69
+ },
70
+ {
71
+ "idx": 7,
72
+ "instance_id": 308,
73
+ "q_score": 0.6666666666666666,
74
+ "success": false,
75
+ "steps": 15295,
76
+ "base_distance_m": 6.85,
77
+ "video": null
78
+ },
79
+ {
80
+ "idx": 8,
81
+ "instance_id": 309,
82
+ "q_score": 0.6666666666666666,
83
+ "success": false,
84
+ "steps": 15295,
85
+ "base_distance_m": 11.93,
86
+ "video": null
87
+ },
88
+ {
89
+ "idx": 9,
90
+ "instance_id": 310,
91
+ "q_score": 0.6666666666666666,
92
+ "success": false,
93
+ "steps": 15295,
94
+ "base_distance_m": 8.17,
95
+ "video": null
96
+ },
97
+ {
98
+ "idx": 10,
99
+ "instance_id": 311,
100
+ "q_score": 0.6666666666666666,
101
+ "success": false,
102
+ "steps": 15295,
103
+ "base_distance_m": 8.81,
104
+ "video": null
105
+ },
106
+ {
107
+ "idx": 11,
108
+ "instance_id": 312,
109
+ "q_score": 0.6666666666666666,
110
+ "success": false,
111
+ "steps": 15295,
112
+ "base_distance_m": 10.01,
113
+ "video": null
114
+ },
115
+ {
116
+ "idx": 12,
117
+ "instance_id": 313,
118
+ "q_score": 0.3333333333333333,
119
+ "success": false,
120
+ "steps": 15295,
121
+ "base_distance_m": 6.77,
122
+ "video": null
123
+ },
124
+ {
125
+ "idx": 13,
126
+ "instance_id": 314,
127
+ "q_score": 0.16666666666666666,
128
+ "success": false,
129
+ "steps": 15295,
130
+ "base_distance_m": 4.25,
131
+ "video": null
132
+ },
133
+ {
134
+ "idx": 14,
135
+ "instance_id": 315,
136
+ "q_score": 0.6666666666666666,
137
+ "success": false,
138
+ "steps": 15295,
139
+ "base_distance_m": 7.23,
140
+ "video": null
141
+ },
142
+ {
143
+ "idx": 15,
144
+ "instance_id": 316,
145
+ "q_score": 0.6666666666666666,
146
+ "success": false,
147
+ "steps": 15295,
148
+ "base_distance_m": 9.89,
149
+ "video": null
150
+ },
151
+ {
152
+ "idx": 16,
153
+ "instance_id": 317,
154
+ "q_score": 0.6666666666666666,
155
+ "success": false,
156
+ "steps": 15295,
157
+ "base_distance_m": 6.83,
158
+ "video": null
159
+ },
160
+ {
161
+ "idx": 17,
162
+ "instance_id": 318,
163
+ "q_score": 0.6666666666666666,
164
+ "success": false,
165
+ "steps": 15295,
166
+ "base_distance_m": 11.91,
167
+ "video": null
168
+ },
169
+ {
170
+ "idx": 18,
171
+ "instance_id": 319,
172
+ "q_score": 0.3333333333333333,
173
+ "success": false,
174
+ "steps": 15295,
175
+ "base_distance_m": 10.69,
176
+ "video": null
177
+ },
178
+ {
179
+ "idx": 19,
180
+ "instance_id": 320,
181
+ "q_score": 1.0,
182
+ "success": true,
183
+ "steps": 12805,
184
+ "base_distance_m": 10.31,
185
+ "video": null
186
+ }
187
+ ]
188
+ }
task5/eval_videos/merged20000/inst301_idx00_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ad2d83cdc6f4cab1da0d1770fabcad050ec39c04beafc78192e3a006084fac6
3
+ size 24660385
task5/eval_videos/merged20000/inst302_idx01_q0.5000.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a3eb2f86dfbddbc4274fe07eb5afc2d1b585a77b0fd64f615a5234cb10af93a
3
+ size 25713859
task5/eval_videos/merged20000/inst303_idx02_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0e88d85d02657e74b9d7097af152ab4a08edc4fefc7484b6a0f3dfd5eb4a4f6
3
+ size 26714770
task5/eval_videos/merged20000/inst304_idx03_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:530ccda006838731cf21e20388ba33fea98abbc507e426eb2df57b17cc73c758
3
+ size 23154662
task5/eval_videos/merged20000/inst305_idx04_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2568cf4554a7bfffde8b0e4c374cab1405c6242067b11849151fc5da9ff32b8e
3
+ size 25045331
task5/eval_videos/merged20000/inst306_idx05_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4092c361e440ba6f04428e0a5a7f3c57295a10c875fc63cda9bed61bf766fab
3
+ size 25760664
task5/eval_videos/merged20000/inst307_idx06_q0.3333.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c62a4d0f8770597bfb7b80c3f91920febe0732dda8eebe8d255c21ea762a2573
3
+ size 23384474
task5/eval_videos/merged20000/inst308_idx07_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6240f195ddb5ff85b6abb69bc9ef6089a3216dd324079193a68be57abce8ed59
3
+ size 26670680
task5/eval_videos/merged20000/inst309_idx08_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54692b134e7fd2448a48480cc33568f339c19b919f5c8407eeea2660004488af
3
+ size 24286997
task5/eval_videos/merged20000/inst310_idx09_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b08bde9acf68992cfba3699b01aee7ef046f2ecf249aa9a7ebd6c3e2f6919f23
3
+ size 25641718
task5/eval_videos/merged20000/inst311_idx10_q0.1667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a77a5cea02a8de8b218fd7e54de86844976f9385e6c825a7bcbed93f95998af
3
+ size 16665539
task5/eval_videos/merged20000/inst312_idx11_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9256206530578c0b2d12ca957da980fef39451d693f7fd4cb1178a478808360
3
+ size 24226738
task5/eval_videos/merged20000/inst313_idx12_q0.3333.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2c148631261fd2d9918734dbca349c6e1383c0e0a4c32324e1b1452b88f702c
3
+ size 18638629
task5/eval_videos/merged20000/inst314_idx13_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:665b9f82de01d26c8e32f9ce1671151d902645b68247c44fe6465e0036d6575c
3
+ size 25073871
task5/eval_videos/merged20000/inst315_idx14_q0.8333.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb149332d6d8af217c21ceb1245235a92b06fe182c12dad5e07eca9bf0a103f3
3
+ size 25068598
task5/eval_videos/merged20000/inst316_idx15_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b8f63f1fc56305189118bd19d418fabc2e9dd3d94832559a5c4a21dec97acc9
3
+ size 23913028
task5/eval_videos/merged20000/inst317_idx16_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1093fb3d046dc2bfd1e40a11458d85c3db9a19b6cf89899e7113e582649ad52a
3
+ size 23692939
task5/eval_videos/merged20000/inst318_idx17_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a0e9afa1997ad0ca670afe41f6e516e87529f7134bb2603fee9cead18b90410
3
+ size 25468264
task5/eval_videos/merged20000/inst319_idx18_q0.8333.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e507923cfb480db9c74e4a7bcfa1bda0d95c4ec152c96bad04a42cb47b51c2b3
3
+ size 26195333
task5/eval_videos/merged20000/inst320_idx19_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acfce8ba34bd3b452970ecc77c543a7b01a321c8e18bed6f3b4ef4bfac790c30
3
+ size 18999159
task5/eval_videos/merged20000/results.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint": "merged20000",
3
+ "n_instances": 20,
4
+ "mean_q": 0.6167,
5
+ "success": 0,
6
+ "episodes": [
7
+ {
8
+ "idx": 0,
9
+ "instance_id": 301,
10
+ "q_score": 0.6666666666666666,
11
+ "success": false,
12
+ "steps": 15295,
13
+ "base_distance_m": 12.23,
14
+ "video": "inst301_idx00_q0.6667.mp4"
15
+ },
16
+ {
17
+ "idx": 1,
18
+ "instance_id": 302,
19
+ "q_score": 0.5,
20
+ "success": false,
21
+ "steps": 15295,
22
+ "base_distance_m": 8.91,
23
+ "video": "inst302_idx01_q0.5000.mp4"
24
+ },
25
+ {
26
+ "idx": 2,
27
+ "instance_id": 303,
28
+ "q_score": 0.6666666666666666,
29
+ "success": false,
30
+ "steps": 15295,
31
+ "base_distance_m": 12.0,
32
+ "video": "inst303_idx02_q0.6667.mp4"
33
+ },
34
+ {
35
+ "idx": 3,
36
+ "instance_id": 304,
37
+ "q_score": 0.6666666666666666,
38
+ "success": false,
39
+ "steps": 15295,
40
+ "base_distance_m": 12.06,
41
+ "video": "inst304_idx03_q0.6667.mp4"
42
+ },
43
+ {
44
+ "idx": 4,
45
+ "instance_id": 305,
46
+ "q_score": 0.6666666666666666,
47
+ "success": false,
48
+ "steps": 15295,
49
+ "base_distance_m": 13.14,
50
+ "video": "inst305_idx04_q0.6667.mp4"
51
+ },
52
+ {
53
+ "idx": 5,
54
+ "instance_id": 306,
55
+ "q_score": 0.6666666666666666,
56
+ "success": false,
57
+ "steps": 15295,
58
+ "base_distance_m": 15.93,
59
+ "video": "inst306_idx05_q0.6667.mp4"
60
+ },
61
+ {
62
+ "idx": 6,
63
+ "instance_id": 307,
64
+ "q_score": 0.3333333333333333,
65
+ "success": false,
66
+ "steps": 15295,
67
+ "base_distance_m": 9.84,
68
+ "video": "inst307_idx06_q0.3333.mp4"
69
+ },
70
+ {
71
+ "idx": 7,
72
+ "instance_id": 308,
73
+ "q_score": 0.6666666666666666,
74
+ "success": false,
75
+ "steps": 15295,
76
+ "base_distance_m": 14.72,
77
+ "video": "inst308_idx07_q0.6667.mp4"
78
+ },
79
+ {
80
+ "idx": 8,
81
+ "instance_id": 309,
82
+ "q_score": 0.6666666666666666,
83
+ "success": false,
84
+ "steps": 15295,
85
+ "base_distance_m": 9.42,
86
+ "video": "inst309_idx08_q0.6667.mp4"
87
+ },
88
+ {
89
+ "idx": 9,
90
+ "instance_id": 310,
91
+ "q_score": 0.6666666666666666,
92
+ "success": false,
93
+ "steps": 15295,
94
+ "base_distance_m": 15.96,
95
+ "video": "inst310_idx09_q0.6667.mp4"
96
+ },
97
+ {
98
+ "idx": 10,
99
+ "instance_id": 311,
100
+ "q_score": 0.16666666666666666,
101
+ "success": false,
102
+ "steps": 15295,
103
+ "base_distance_m": 2.91,
104
+ "video": "inst311_idx10_q0.1667.mp4"
105
+ },
106
+ {
107
+ "idx": 11,
108
+ "instance_id": 312,
109
+ "q_score": 0.6666666666666666,
110
+ "success": false,
111
+ "steps": 15295,
112
+ "base_distance_m": 12.06,
113
+ "video": "inst312_idx11_q0.6667.mp4"
114
+ },
115
+ {
116
+ "idx": 12,
117
+ "instance_id": 313,
118
+ "q_score": 0.3333333333333333,
119
+ "success": false,
120
+ "steps": 15295,
121
+ "base_distance_m": 5.34,
122
+ "video": "inst313_idx12_q0.3333.mp4"
123
+ },
124
+ {
125
+ "idx": 13,
126
+ "instance_id": 314,
127
+ "q_score": 0.6666666666666666,
128
+ "success": false,
129
+ "steps": 15295,
130
+ "base_distance_m": 10.72,
131
+ "video": "inst314_idx13_q0.6667.mp4"
132
+ },
133
+ {
134
+ "idx": 14,
135
+ "instance_id": 315,
136
+ "q_score": 0.8333333333333334,
137
+ "success": false,
138
+ "steps": 15295,
139
+ "base_distance_m": 12.59,
140
+ "video": "inst315_idx14_q0.8333.mp4"
141
+ },
142
+ {
143
+ "idx": 15,
144
+ "instance_id": 316,
145
+ "q_score": 0.6666666666666666,
146
+ "success": false,
147
+ "steps": 15295,
148
+ "base_distance_m": 10.02,
149
+ "video": "inst316_idx15_q0.6667.mp4"
150
+ },
151
+ {
152
+ "idx": 16,
153
+ "instance_id": 317,
154
+ "q_score": 0.6666666666666666,
155
+ "success": false,
156
+ "steps": 15295,
157
+ "base_distance_m": 9.37,
158
+ "video": "inst317_idx16_q0.6667.mp4"
159
+ },
160
+ {
161
+ "idx": 17,
162
+ "instance_id": 318,
163
+ "q_score": 0.6666666666666666,
164
+ "success": false,
165
+ "steps": 15295,
166
+ "base_distance_m": 10.32,
167
+ "video": "inst318_idx17_q0.6667.mp4"
168
+ },
169
+ {
170
+ "idx": 18,
171
+ "instance_id": 319,
172
+ "q_score": 0.8333333333333334,
173
+ "success": false,
174
+ "steps": 15295,
175
+ "base_distance_m": 11.51,
176
+ "video": "inst319_idx18_q0.8333.mp4"
177
+ },
178
+ {
179
+ "idx": 19,
180
+ "instance_id": 320,
181
+ "q_score": 0.6666666666666666,
182
+ "success": false,
183
+ "steps": 15295,
184
+ "base_distance_m": 6.15,
185
+ "video": "inst320_idx19_q0.6667.mp4"
186
+ }
187
+ ]
188
+ }
task5/eval_videos/merged39999/inst301_idx00_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d63b2bd3a9b6ea30de2ece6d51c8fa7dd737206aeacb270f30a31fda177c67cb
3
+ size 27110452
task5/eval_videos/merged39999/inst302_idx01_q1.0000.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d13085d932c8479c6ffd2374cce14443db6c83294e541f8439aa3539dff21753
3
+ size 14002685
task5/eval_videos/merged39999/inst303_idx02_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92bdd08dc32c372381fda35e109f479f8f7cb8bc978f437d6f842f17fff1780f
3
+ size 23659234
task5/eval_videos/merged39999/inst304_idx03_q0.8333.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db77a44c4dfbb4b67184be9bd200c772a2a437784fcdd31b8d79bd7837b6e5f9
3
+ size 23771839
task5/eval_videos/merged39999/inst305_idx04_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5171091e8e62840329835d3aa74b2cf77ce76671d3dfdd7011724c937850531
3
+ size 22262788
task5/eval_videos/merged39999/inst306_idx05_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:664d588d2f763776fa88f6bb383c542e5bf878650ba901ad4b803739b386e2d1
3
+ size 23624736
task5/eval_videos/merged39999/inst307_idx06_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ae634114275527fb8e786ed92d1a3dac2a8ebfd6678395bcb76972037a3ad86
3
+ size 24216463
task5/eval_videos/merged39999/inst308_idx07_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e991384a481064cbab0dc56dcf9265026c7a6135f2d2f0916364706f2a761474
3
+ size 25094148
task5/eval_videos/merged39999/inst309_idx08_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99250753c5b4463680e49d40d2bbbb637c3af83d83b1ae6045b55230389827b
3
+ size 30891020
task5/eval_videos/merged39999/inst310_idx09_q0.3333.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c9ef2d51d59d2bfabbc4558bfc6d7e5ac9c491bca94219d1cb1c94894a20ffa
3
+ size 20989447
task5/eval_videos/merged39999/inst311_idx10_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9182508f4ce902ee5d8f1c9a5f29dd5e6b7d0acb929070f8936115e4451ebf6
3
+ size 21777944
task5/eval_videos/merged39999/inst312_idx11_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0930591d1483ccb546f33dd161f6ce7aafad44a88e25d4722391619acb220061
3
+ size 22627217
task5/eval_videos/merged39999/inst313_idx12_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e95054ae5596ca3d91c556a8d4b5697190950271a7f65c12f068f5cac76dd0
3
+ size 22411036
task5/eval_videos/merged39999/inst314_idx13_q0.5000.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4e3dc9838d590ec91ab1f43fec6107f503f99b5ebf6c6c0027099ae77a88980
3
+ size 27182794
task5/eval_videos/merged39999/inst315_idx14_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce3a2385982381f7d254db31a42f958d61b37a8d1afa8bbba565314d27bd4268
3
+ size 25988196
task5/eval_videos/merged39999/inst316_idx15_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95dfb2ad703352666c8ceea99bca4ef2cdc5b2b537e28506ad04a14938d007f3
3
+ size 19994424
task5/eval_videos/merged39999/inst317_idx16_q0.1667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c008c5ad06d14d0c3d0db3f887182b52f30e3966efaf89caa18f2fd0910c8490
3
+ size 21227732
task5/eval_videos/merged39999/inst318_idx17_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e07587752e727c50a6a5f827815c7bc88d8cbc4f9b1891fac047d730450e49a1
3
+ size 23508505
task5/eval_videos/merged39999/inst319_idx18_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26e26e95345cec9d477a6945a6d4557efa81d21685c152e30f2f39a8fceb60e2
3
+ size 28430425
task5/eval_videos/merged39999/inst320_idx19_q0.6667.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8211a6ac588ad60e6e65b1f8bd902593b8fd58bee0aeb151de5783cf3ff1ac2
3
+ size 22820879
task5/eval_videos/merged39999/results.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint": "merged39999",
3
+ "n_instances": 20,
4
+ "mean_q": 0.6417,
5
+ "success": 1,
6
+ "episodes": [
7
+ {
8
+ "idx": 0,
9
+ "instance_id": 301,
10
+ "q_score": 0.6666666666666666,
11
+ "success": false,
12
+ "steps": 15295,
13
+ "base_distance_m": 10.76,
14
+ "video": "inst301_idx00_q0.6667.mp4"
15
+ },
16
+ {
17
+ "idx": 1,
18
+ "instance_id": 302,
19
+ "q_score": 1.0,
20
+ "success": true,
21
+ "steps": 7538,
22
+ "base_distance_m": 10.18,
23
+ "video": "inst302_idx01_q1.0000.mp4"
24
+ },
25
+ {
26
+ "idx": 2,
27
+ "instance_id": 303,
28
+ "q_score": 0.6666666666666666,
29
+ "success": false,
30
+ "steps": 15295,
31
+ "base_distance_m": 8.58,
32
+ "video": "inst303_idx02_q0.6667.mp4"
33
+ },
34
+ {
35
+ "idx": 3,
36
+ "instance_id": 304,
37
+ "q_score": 0.8333333333333334,
38
+ "success": false,
39
+ "steps": 15295,
40
+ "base_distance_m": 10.52,
41
+ "video": "inst304_idx03_q0.8333.mp4"
42
+ },
43
+ {
44
+ "idx": 4,
45
+ "instance_id": 305,
46
+ "q_score": 0.6666666666666666,
47
+ "success": false,
48
+ "steps": 15295,
49
+ "base_distance_m": 9.47,
50
+ "video": "inst305_idx04_q0.6667.mp4"
51
+ },
52
+ {
53
+ "idx": 5,
54
+ "instance_id": 306,
55
+ "q_score": 0.6666666666666666,
56
+ "success": false,
57
+ "steps": 15295,
58
+ "base_distance_m": 10.44,
59
+ "video": "inst306_idx05_q0.6667.mp4"
60
+ },
61
+ {
62
+ "idx": 6,
63
+ "instance_id": 307,
64
+ "q_score": 0.6666666666666666,
65
+ "success": false,
66
+ "steps": 15295,
67
+ "base_distance_m": 7.97,
68
+ "video": "inst307_idx06_q0.6667.mp4"
69
+ },
70
+ {
71
+ "idx": 7,
72
+ "instance_id": 308,
73
+ "q_score": 0.6666666666666666,
74
+ "success": false,
75
+ "steps": 15295,
76
+ "base_distance_m": 10.65,
77
+ "video": "inst308_idx07_q0.6667.mp4"
78
+ },
79
+ {
80
+ "idx": 8,
81
+ "instance_id": 309,
82
+ "q_score": 0.6666666666666666,
83
+ "success": false,
84
+ "steps": 15295,
85
+ "base_distance_m": 14.42,
86
+ "video": "inst309_idx08_q0.6667.mp4"
87
+ },
88
+ {
89
+ "idx": 9,
90
+ "instance_id": 310,
91
+ "q_score": 0.3333333333333333,
92
+ "success": false,
93
+ "steps": 15295,
94
+ "base_distance_m": 6.93,
95
+ "video": "inst310_idx09_q0.3333.mp4"
96
+ },
97
+ {
98
+ "idx": 10,
99
+ "instance_id": 311,
100
+ "q_score": 0.6666666666666666,
101
+ "success": false,
102
+ "steps": 15295,
103
+ "base_distance_m": 8.44,
104
+ "video": "inst311_idx10_q0.6667.mp4"
105
+ },
106
+ {
107
+ "idx": 11,
108
+ "instance_id": 312,
109
+ "q_score": 0.6666666666666666,
110
+ "success": false,
111
+ "steps": 15295,
112
+ "base_distance_m": 8.31,
113
+ "video": "inst312_idx11_q0.6667.mp4"
114
+ },
115
+ {
116
+ "idx": 12,
117
+ "instance_id": 313,
118
+ "q_score": 0.6666666666666666,
119
+ "success": false,
120
+ "steps": 15295,
121
+ "base_distance_m": 10.29,
122
+ "video": "inst313_idx12_q0.6667.mp4"
123
+ },
124
+ {
125
+ "idx": 13,
126
+ "instance_id": 314,
127
+ "q_score": 0.5,
128
+ "success": false,
129
+ "steps": 15295,
130
+ "base_distance_m": 8.97,
131
+ "video": "inst314_idx13_q0.5000.mp4"
132
+ },
133
+ {
134
+ "idx": 14,
135
+ "instance_id": 315,
136
+ "q_score": 0.6666666666666666,
137
+ "success": false,
138
+ "steps": 15295,
139
+ "base_distance_m": 12.09,
140
+ "video": "inst315_idx14_q0.6667.mp4"
141
+ },
142
+ {
143
+ "idx": 15,
144
+ "instance_id": 316,
145
+ "q_score": 0.6666666666666666,
146
+ "success": false,
147
+ "steps": 15295,
148
+ "base_distance_m": 6.87,
149
+ "video": "inst316_idx15_q0.6667.mp4"
150
+ },
151
+ {
152
+ "idx": 16,
153
+ "instance_id": 317,
154
+ "q_score": 0.16666666666666666,
155
+ "success": false,
156
+ "steps": 15295,
157
+ "base_distance_m": 4.88,
158
+ "video": "inst317_idx16_q0.1667.mp4"
159
+ },
160
+ {
161
+ "idx": 17,
162
+ "instance_id": 318,
163
+ "q_score": 0.6666666666666666,
164
+ "success": false,
165
+ "steps": 15295,
166
+ "base_distance_m": 11.04,
167
+ "video": "inst318_idx17_q0.6667.mp4"
168
+ },
169
+ {
170
+ "idx": 18,
171
+ "instance_id": 319,
172
+ "q_score": 0.6666666666666666,
173
+ "success": false,
174
+ "steps": 15295,
175
+ "base_distance_m": 12.53,
176
+ "video": "inst319_idx18_q0.6667.mp4"
177
+ },
178
+ {
179
+ "idx": 19,
180
+ "instance_id": 320,
181
+ "q_score": 0.6666666666666666,
182
+ "success": false,
183
+ "steps": 15295,
184
+ "base_distance_m": 10.39,
185
+ "video": "inst320_idx19_q0.6667.mp4"
186
+ }
187
+ ]
188
+ }