Initial commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.19 +/- 0.12
+      value: -0.21 +/- 0.12
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90e3e100db4fca4b73933111ad13a74ca725927cddd9f3862ce5e7780661844e
+oid sha256:0461e013bcc77e31c6b08549e7869fc25aad0d1237791a7b6a19b2801892cff1
 size 114068

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23c8c1f8744199f85fd53acd47e2d6a731474744b233e1bdc03188cc27e4b147
+size 619923

results.json

@@ -1 +1 @@
-{"mean_reward": -0.18785967007279397, "std_reward": 0.12227737096631787, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-04T10:43:54.394756"}
+{"mean_reward": -0.21362647283822297, "std_reward": 0.11941287364907632, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-04T11:12:59.684405"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8712cf2ae4082148cad8a109a6c0174e9c6872070b6841fcbae719d3d03cb0f2
-size 2644
+oid sha256:9da380e8a275719341a991c916e0e1c110ebbee3a01e54fc495988bf2c4d2841
+size 2718