Initial commit

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 videos/a2c-replay-step-0-to-step-1000.mp4 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: -0.25 +/- 0.11
+      value: -0.17 +/- 0.09
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e6d0f22755f4bcea316f5710dfe2f6a2e7a6d5b1fc8b20341921f1fafce034a
+oid sha256:f40c99ecb2cee184f7d2b74e2f2083ee63f9b96cef03299f24573e261ab9725c
 size 1146754

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ded89ec0bf2c204a7320f4dad0f7a974f8b9d881ecfa3cd8c988a2606ce44d5b
+size 619765

results.json

@@ -1 +1 @@
-{"mean_reward": -0.2504867392592132, "std_reward": 0.10866736645329612, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-05T23:33:13.188075"}
+{"mean_reward": -0.16853519901633263, "std_reward": 0.08684421677663448, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-05T23:43:48.861008"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ffa4455b8c1b61d343a1149c3cd61e9b86bd3f6dcd39429d5e44e9cf35e171e
-size 2650
+oid sha256:f3f71722775853f635d0d9ac0a1f355238b03df377bf1ccd6e2cbcdc3157ce74
+size 2637