Initial commit

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 2.00 +/- 0.00
+      value: 2.70 +/- 4.12
       name: mean_reward
     task:
       type: reinforcement-learning

a2c-CartPole-v1.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01afe793b7a45e279cb63133e6c9eb394fc986e2c602475b03aba8c7fcf0926a
-size 13707008
+oid sha256:a9e1cebc24ae5de06b95151665be073ebff9921cce5e3eff6b3178ed2c400a15
+size 13708751

a2c-CartPole-v1/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7675208fcacac3de01a03dc7bdc5229acfce355f0510a6d91696264206188c8f
+oid sha256:88a7af4eed1cc5f0eaeaff74c70d3f78b3e2da3e1a6f788c5c8f3c8e2b098bda
 size 6750209

a2c-CartPole-v1/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c181243e15910246de36b026323ff9cc6038cdefd53890be3c08d24236db0e7
+oid sha256:4be919a0834d1d195a208806c8f30fd2a2be9bac956babad7776d0bd551e1640
 size 6750913

results.json

@@ -1 +1 @@
-{"mean_reward": 2.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-07T14:38:36.595854"}
+{"mean_reward": 2.7, "std_reward": 4.124318125460256, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-07T16:00:20.235804"}