Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.22 +/- 0.13
+      value: -0.22 +/- 0.09
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c13d5af8b5e07139db0374eec5d936fa1f492f4a9a84f23fc3fff697512e832
+oid sha256:7cd72b518a8cdacf506242a6703139658dcca59f9fcdc8cddbc116110d53326c
 size 110344

results.json

@@ -1 +1 @@
-{"mean_reward": -0.21819396130740643, "std_reward": 0.13112975468933813, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-11T10:27:36.932447"}
+{"mean_reward": -0.22210551640018822, "std_reward": 0.08996773204107812, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-11T10:30:53.894590"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c530a955e71cacf0a7a8c812385704b823727eb6d5b215eac2845953092ed387
-size 2646
+oid sha256:0313883331b6abd740e406d872ffa984d6b6190891d523ebf07a1994f9cbba5c
+size 2659