First A2C agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -1.93 +/- 2.61
+      value: -0.92 +/- 2.06
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7db7bfa29efe7a923f0c26a4aaa84086eb545813788ce6b3927e5efcb675a10
+oid sha256:c92f431acd9054112637f34501701d1645b889f0d41eb1d67dc0eea38d7d67fb
 size 110344

results.json

@@ -1 +1 @@
-{"mean_reward": -1.9259607825428247, "std_reward": 2.6136463470193427, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-16T16:01:19.016635"}
+{"mean_reward": -0.9191864280961454, "std_reward": 2.0569771644449797, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-16T16:17:23.610329"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df487eeed92a06f50cb4902938c534ef6c36411e522538477190cc93923cb7a1
-size 2646
+oid sha256:c0c6c9b978ebd1193458475b9b0564661f02752b8112e1ad032154e22eaea3cc
+size 2659