Initial commit, slm friends

README.md

@@ -16,7 +16,7 @@ model-index:
       type: AntBulletEnv-v0
     metrics:
     - type: mean_reward
-      value: 1447.38 +/- 304.16
+      value: 1573.42 +/- 109.04
       name: mean_reward
       verified: false
 ---

a2c-AntBulletEnv-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49dd36df0068ba849c7bdaf380a8663d0db2b128a76ab610f1b655a99d090825
+oid sha256:f2b72537272cee06b3c6acf1745f339aff1df80fa1a71d794d5675a7a1fee310
 size 129260

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b35013ca5afa5cd61b90b8270c430a7b049d30726355e5e6b1337d10ea0225e
-size 1232043
+oid sha256:82cd5da81b382351d66fc7fd2f8f24df477f887633f5b347a49663cf9bae43be
+size 907715

results.json

@@ -1 +1 @@
-{"mean_reward": 1447.3761132762302, "std_reward": 304.161701074167, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-20T14:07:55.194129"}
+{"mean_reward": 1573.4197836809676, "std_reward": 109.03575144255275, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-20T14:12:36.571005"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd799b1041fe1f420da186d5ae7cda26dc4417138ea2db8b99862dd8c662218f
+oid sha256:a03b95e88e7427420974f9721b6143a68f9bd96b191370e915dd423840154c09
 size 2136