Publish latest local CUDA training weights
Browse files- README.md +15 -15
- bdi/affect.npz +1 -1
- bdi/belief.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 +15 -15
- rssm/epoch_10.pt +2 -2
- rssm/epoch_100.pt +2 -2
- rssm/epoch_20.pt +2 -2
- rssm/epoch_30.pt +2 -2
- rssm/epoch_40.pt +2 -2
- rssm/epoch_50.pt +2 -2
- rssm/epoch_60.pt +2 -2
- rssm/epoch_70.pt +2 -2
- rssm/epoch_80.pt +2 -2
- rssm/epoch_90.pt +2 -2
- rssm/final.pt +2 -2
README.md
CHANGED
|
@@ -36,29 +36,29 @@ Trained on Jetson Orin Nano (8 GB) using synthetic observation sequences.
|
|
| 36 |
"mcts_tuning": {
|
| 37 |
"best_ucb_c": 1.41,
|
| 38 |
"ucb_0.5": {
|
| 39 |
-
"mean_reward":
|
| 40 |
-
"p50_ms":
|
| 41 |
-
"p95_ms":
|
| 42 |
},
|
| 43 |
"ucb_1.0": {
|
| 44 |
-
"mean_reward":
|
| 45 |
-
"p50_ms":
|
| 46 |
-
"p95_ms":
|
| 47 |
},
|
| 48 |
"ucb_1.41": {
|
| 49 |
-
"mean_reward":
|
| 50 |
-
"p50_ms":
|
| 51 |
-
"p95_ms":
|
| 52 |
},
|
| 53 |
"ucb_2.0": {
|
| 54 |
-
"mean_reward":
|
| 55 |
-
"p50_ms":
|
| 56 |
-
"p95_ms":
|
| 57 |
},
|
| 58 |
"ucb_3.0": {
|
| 59 |
-
"mean_reward":
|
| 60 |
-
"p50_ms":
|
| 61 |
-
"p95_ms":
|
| 62 |
}
|
| 63 |
}
|
| 64 |
}
|
|
|
|
| 36 |
"mcts_tuning": {
|
| 37 |
"best_ucb_c": 1.41,
|
| 38 |
"ucb_0.5": {
|
| 39 |
+
"mean_reward": 0.1749,
|
| 40 |
+
"p50_ms": 110.0,
|
| 41 |
+
"p95_ms": 125.0
|
| 42 |
},
|
| 43 |
"ucb_1.0": {
|
| 44 |
+
"mean_reward": 0.172,
|
| 45 |
+
"p50_ms": 109.0,
|
| 46 |
+
"p95_ms": 125.0
|
| 47 |
},
|
| 48 |
"ucb_1.41": {
|
| 49 |
+
"mean_reward": 0.145,
|
| 50 |
+
"p50_ms": 109.0,
|
| 51 |
+
"p95_ms": 125.0
|
| 52 |
},
|
| 53 |
"ucb_2.0": {
|
| 54 |
+
"mean_reward": 0.223,
|
| 55 |
+
"p50_ms": 109.0,
|
| 56 |
+
"p95_ms": 125.0
|
| 57 |
},
|
| 58 |
"ucb_3.0": {
|
| 59 |
+
"mean_reward": 0.4133,
|
| 60 |
+
"p50_ms": 109.0,
|
| 61 |
+
"p95_ms": 125.0
|
| 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 sha256:04a55c31e7679f05b78b927e6941dc4502754cb7a3e51ddccf696f30c263700d
|
| 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 sha256:4d43fd224cd625d9b71bf104a173597b8b5487f523fd634c7c5629501b397b05
|
| 3 |
size 198598
|
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 sha256:026a2e8afb53a478511128302c7b5ddf0f0df47a6b2289d1038d6bdd33d73c74
|
| 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 sha256:05047f7fe2146e65b346fddcc455f8d66d9e1f9a04962758597cb23d7ddc6ae5
|
| 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 sha256:05c6bbac29246a563e2abb2802f6bdf8c75d602ded650a5fe3539d6862f03e57
|
| 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 sha256:26c595b3e868808a29dbd50df9e3f1d0bea41c2ac49dce234cc29d255f1b1389
|
| 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 sha256:05c6bbac29246a563e2abb2802f6bdf8c75d602ded650a5fe3539d6862f03e57
|
| 3 |
size 18386
|
mcts/tuned_config.json
CHANGED
|
@@ -1,28 +1,28 @@
|
|
| 1 |
{
|
| 2 |
"ucb_0.5": {
|
| 3 |
-
"mean_reward":
|
| 4 |
-
"p50_ms":
|
| 5 |
-
"p95_ms":
|
| 6 |
},
|
| 7 |
"ucb_1.0": {
|
| 8 |
-
"mean_reward":
|
| 9 |
-
"p50_ms":
|
| 10 |
-
"p95_ms":
|
| 11 |
},
|
| 12 |
"ucb_1.41": {
|
| 13 |
-
"mean_reward":
|
| 14 |
-
"p50_ms":
|
| 15 |
-
"p95_ms":
|
| 16 |
},
|
| 17 |
"ucb_2.0": {
|
| 18 |
-
"mean_reward":
|
| 19 |
-
"p50_ms":
|
| 20 |
-
"p95_ms":
|
| 21 |
},
|
| 22 |
"ucb_3.0": {
|
| 23 |
-
"mean_reward":
|
| 24 |
-
"p50_ms":
|
| 25 |
-
"p95_ms":
|
| 26 |
},
|
| 27 |
"best_ucb_c": 1.41
|
| 28 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"ucb_0.5": {
|
| 3 |
+
"mean_reward": 0.1749,
|
| 4 |
+
"p50_ms": 110.0,
|
| 5 |
+
"p95_ms": 125.0
|
| 6 |
},
|
| 7 |
"ucb_1.0": {
|
| 8 |
+
"mean_reward": 0.172,
|
| 9 |
+
"p50_ms": 109.0,
|
| 10 |
+
"p95_ms": 125.0
|
| 11 |
},
|
| 12 |
"ucb_1.41": {
|
| 13 |
+
"mean_reward": 0.145,
|
| 14 |
+
"p50_ms": 109.0,
|
| 15 |
+
"p95_ms": 125.0
|
| 16 |
},
|
| 17 |
"ucb_2.0": {
|
| 18 |
+
"mean_reward": 0.223,
|
| 19 |
+
"p50_ms": 109.0,
|
| 20 |
+
"p95_ms": 125.0
|
| 21 |
},
|
| 22 |
"ucb_3.0": {
|
| 23 |
+
"mean_reward": 0.4133,
|
| 24 |
+
"p50_ms": 109.0,
|
| 25 |
+
"p95_ms": 125.0
|
| 26 |
},
|
| 27 |
"best_ucb_c": 1.41
|
| 28 |
}
|
rssm/epoch_10.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83800e2d4cd4d040d206e54a28c270e71a0b12a3ba6ff7dee6e40846949e41a3
|
| 3 |
+
size 6307407
|
rssm/epoch_100.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bd2e9330f78189c4e3fc2b3f53af664f9604377609f3e7a4edbf07a25e01478
|
| 3 |
+
size 6307490
|
rssm/epoch_20.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ba3bd65d2a520b97516ce5fac758822d4408e96284e0ca86a4132f1b2bf9bc4
|
| 3 |
+
size 6307407
|
rssm/epoch_30.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae9613a0a9fe9a5c8542db07d0a434c54da635a7d53488386fa035eaa99b6f89
|
| 3 |
+
size 6307407
|
rssm/epoch_40.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cdc58666efafe406e0de21c1f971d338affec3b690f995972e93cf073b24066
|
| 3 |
+
size 6307407
|
rssm/epoch_50.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3155fa1b407b4d1287aa1e6154d599a9427375fcbb13ee00cd9c4ed0fe61b4e8
|
| 3 |
+
size 6307407
|
rssm/epoch_60.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8fab986f82da0b31022b995378b9c9763c6fa53eaffa8b520797fdba92e30292
|
| 3 |
+
size 6307407
|
rssm/epoch_70.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfa63d7c126be09dba6733f3a00c9ca0f3ae9c05559812172b9138b7630a0696
|
| 3 |
+
size 6307407
|
rssm/epoch_80.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:736065bb85b1d41a7446a0811db5783739c809a33a469cd67dca0bc7f390bce3
|
| 3 |
+
size 6307407
|
rssm/epoch_90.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e13b410f3bb2bdae5d6d60379a0925ec7ceae4daa85ea7c41daa33f5cb8e071e
|
| 3 |
+
size 6307407
|
rssm/final.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55ada4687da88f3deb1b847808c8b0625069c79a5f6db80aed8f79bccabbc92f
|
| 3 |
+
size 2116713
|