post-refactor-retrain full pipeline v0.3.0
Browse files- README.md +11 -11
- bdi/affect.npz +1 -1
- bdi/belief.npz +1 -1
- bdi/belief_norm_stats.npz +1 -1
- bdi/desire.npz +1 -1
- bdi/intention.npz +1 -1
- constitutional_rl/policy.npz +1 -1
- constitutional_rl/value.npz +1 -1
- mcts/policy_init.npz +1 -1
- mcts/tuned_config.json +11 -11
- rssm/epoch_100.pt +1 -1
- rssm/epoch_125.pt +1 -1
- rssm/epoch_150.pt +1 -1
- rssm/epoch_175.pt +1 -1
- rssm/epoch_200.pt +1 -1
- rssm/epoch_25.pt +1 -1
- rssm/epoch_50.pt +1 -1
- rssm/epoch_75.pt +1 -1
- rssm/final.pt +1 -1
README.md
CHANGED
|
@@ -34,31 +34,31 @@ Trained on Jetson Orin Nano (8 GB) using synthetic observation sequences.
|
|
| 34 |
```json
|
| 35 |
{
|
| 36 |
"mcts_tuning": {
|
| 37 |
-
"best_ucb_c":
|
| 38 |
"ucb_0.5": {
|
| 39 |
-
"mean_reward":
|
| 40 |
"p50_ms": 16.0,
|
| 41 |
-
"p95_ms":
|
| 42 |
},
|
| 43 |
"ucb_1.0": {
|
| 44 |
-
"mean_reward":
|
| 45 |
"p50_ms": 16.0,
|
| 46 |
-
"p95_ms":
|
| 47 |
},
|
| 48 |
"ucb_1.41": {
|
| 49 |
-
"mean_reward":
|
| 50 |
"p50_ms": 16.0,
|
| 51 |
-
"p95_ms":
|
| 52 |
},
|
| 53 |
"ucb_2.0": {
|
| 54 |
-
"mean_reward":
|
| 55 |
"p50_ms": 16.0,
|
| 56 |
-
"p95_ms":
|
| 57 |
},
|
| 58 |
"ucb_3.0": {
|
| 59 |
-
"mean_reward":
|
| 60 |
"p50_ms": 16.0,
|
| 61 |
-
"p95_ms":
|
| 62 |
}
|
| 63 |
}
|
| 64 |
}
|
|
|
|
| 34 |
```json
|
| 35 |
{
|
| 36 |
"mcts_tuning": {
|
| 37 |
+
"best_ucb_c": 1.41,
|
| 38 |
"ucb_0.5": {
|
| 39 |
+
"mean_reward": 0.169,
|
| 40 |
"p50_ms": 16.0,
|
| 41 |
+
"p95_ms": 31.0
|
| 42 |
},
|
| 43 |
"ucb_1.0": {
|
| 44 |
+
"mean_reward": 0.371,
|
| 45 |
"p50_ms": 16.0,
|
| 46 |
+
"p95_ms": 16.0
|
| 47 |
},
|
| 48 |
"ucb_1.41": {
|
| 49 |
+
"mean_reward": 0.4844,
|
| 50 |
"p50_ms": 16.0,
|
| 51 |
+
"p95_ms": 16.0
|
| 52 |
},
|
| 53 |
"ucb_2.0": {
|
| 54 |
+
"mean_reward": 0.298,
|
| 55 |
"p50_ms": 16.0,
|
| 56 |
+
"p95_ms": 16.0
|
| 57 |
},
|
| 58 |
"ucb_3.0": {
|
| 59 |
+
"mean_reward": 0.1039,
|
| 60 |
"p50_ms": 16.0,
|
| 61 |
+
"p95_ms": 31.0
|
| 62 |
}
|
| 63 |
}
|
| 64 |
}
|
bdi/affect.npz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1094
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dace9a617bcf102e431207ca07a337f76706144a9d0d412336f36dc13a75b402
|
| 3 |
size 1094
|
bdi/belief.npz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 198598
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2703cd4ce8b595ac15e9617d1aae75c5d990c84a82679ddab3bf0c6602d91f60
|
| 3 |
size 198598
|
bdi/belief_norm_stats.npz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2548
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1d8879e1d996773caf9e704f85fe8e2dfa35ff6db2a74f8b6f1214a31ba8f65
|
| 3 |
size 2548
|
bdi/desire.npz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 33518
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad93d785f99e57ccbe5a95ba74501425b0f2bca2114edf5861a983cc25db6e0b
|
| 3 |
size 33518
|
bdi/intention.npz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3094
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3187b8a5ef15a4d601c6f2395dd56bfc802db49fdfafcb57d1fb9b9693d4aa4c
|
| 3 |
size 3094
|
constitutional_rl/policy.npz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 18386
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38a0a9d37a8c701f47075a951c351aaaf4caedebe98b5591f6185a75e271e24b
|
| 3 |
size 18386
|
constitutional_rl/value.npz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 17866
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3926207593e0ecfbef4fd3771d60ee0d98f83c5a8d0f1e32b489ed458b5bbc8
|
| 3 |
size 17866
|
mcts/policy_init.npz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 18386
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38a0a9d37a8c701f47075a951c351aaaf4caedebe98b5591f6185a75e271e24b
|
| 3 |
size 18386
|
mcts/tuned_config.json
CHANGED
|
@@ -1,28 +1,28 @@
|
|
| 1 |
{
|
| 2 |
"ucb_0.5": {
|
| 3 |
-
"mean_reward":
|
| 4 |
"p50_ms": 16.0,
|
| 5 |
-
"p95_ms":
|
| 6 |
},
|
| 7 |
"ucb_1.0": {
|
| 8 |
-
"mean_reward":
|
| 9 |
"p50_ms": 16.0,
|
| 10 |
-
"p95_ms":
|
| 11 |
},
|
| 12 |
"ucb_1.41": {
|
| 13 |
-
"mean_reward":
|
| 14 |
"p50_ms": 16.0,
|
| 15 |
-
"p95_ms":
|
| 16 |
},
|
| 17 |
"ucb_2.0": {
|
| 18 |
-
"mean_reward":
|
| 19 |
"p50_ms": 16.0,
|
| 20 |
-
"p95_ms":
|
| 21 |
},
|
| 22 |
"ucb_3.0": {
|
| 23 |
-
"mean_reward":
|
| 24 |
"p50_ms": 16.0,
|
| 25 |
-
"p95_ms":
|
| 26 |
},
|
| 27 |
-
"best_ucb_c":
|
| 28 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"ucb_0.5": {
|
| 3 |
+
"mean_reward": 0.169,
|
| 4 |
"p50_ms": 16.0,
|
| 5 |
+
"p95_ms": 31.0
|
| 6 |
},
|
| 7 |
"ucb_1.0": {
|
| 8 |
+
"mean_reward": 0.371,
|
| 9 |
"p50_ms": 16.0,
|
| 10 |
+
"p95_ms": 16.0
|
| 11 |
},
|
| 12 |
"ucb_1.41": {
|
| 13 |
+
"mean_reward": 0.4844,
|
| 14 |
"p50_ms": 16.0,
|
| 15 |
+
"p95_ms": 16.0
|
| 16 |
},
|
| 17 |
"ucb_2.0": {
|
| 18 |
+
"mean_reward": 0.298,
|
| 19 |
"p50_ms": 16.0,
|
| 20 |
+
"p95_ms": 16.0
|
| 21 |
},
|
| 22 |
"ucb_3.0": {
|
| 23 |
+
"mean_reward": 0.1039,
|
| 24 |
"p50_ms": 16.0,
|
| 25 |
+
"p95_ms": 31.0
|
| 26 |
},
|
| 27 |
+
"best_ucb_c": 1.41
|
| 28 |
}
|
rssm/epoch_100.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6183780
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:877fc561e625672e100f2268afe8f0258b074e8d46d1878725dc53ab855749c7
|
| 3 |
size 6183780
|
rssm/epoch_125.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6183780
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0fa8fc92633af3dded9cad682b1839d23a9807feab8ebac64e4d7f43452da11
|
| 3 |
size 6183780
|
rssm/epoch_150.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6183780
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85f37ac7f51b11394808bb8872d5c0c58465f6c67858faaab42f72aa1dea6f3e
|
| 3 |
size 6183780
|
rssm/epoch_175.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6183780
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6745772d2fd73d6ca7ea4f2c3644eacfa1f5f6364b127762a7a9e73b897fcb39
|
| 3 |
size 6183780
|
rssm/epoch_200.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6183780
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c6bda4c1148a0de2de0d98ae5fdded47d0cdcba21d9043c34fcca439c1e2c4d
|
| 3 |
size 6183780
|
rssm/epoch_25.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6183699
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af81e2c0cf3a21ef6ae18ad4dbf0ca32787b5b7f5fd2cd3c030fa0e9b887f477
|
| 3 |
size 6183699
|
rssm/epoch_50.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6183699
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6208f8d832d1ca7c561640bc933813f5388fc84100cc9cc69ece20fa03461ddb
|
| 3 |
size 6183699
|
rssm/epoch_75.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6183699
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1279a147409b963f74167ee01b5aefd935e22493e9b12c8334f54b300e124ec2
|
| 3 |
size 6183699
|
rssm/final.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2058739
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc9f9396ea21134f2aa474969362d0efe5f045f818ace2d90ec29b7425bfb077
|
| 3 |
size 2058739
|