Initial commit

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 2.70 +/- 4.12
+      value: 16.90 +/- 6.92
       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:a9e1cebc24ae5de06b95151665be073ebff9921cce5e3eff6b3178ed2c400a15
-size 13708751
+oid sha256:4461359cd6f6089fdf260b81fe0717f9b086c0e9636cee09133a7d9adfeb3e84
+size 20462349

a2c-CartPole-v1/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88a7af4eed1cc5f0eaeaff74c70d3f78b3e2da3e1a6f788c5c8f3c8e2b098bda
-size 6750209
+oid sha256:03ba15e5c9e99f3d8d1c16717d7ddd79b44b2e8dbd8eebb52e92e935b9d0b81c
+size 13503097

a2c-CartPole-v1/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4be919a0834d1d195a208806c8f30fd2a2be9bac956babad7776d0bd551e1640
+oid sha256:6605e07ea0a722fcbdfbff869fd26fef47bdde534579cafd0ad0957caad16010
 size 6750913

results.json

@@ -1 +1 @@
-{"mean_reward": 2.7, "std_reward": 4.124318125460256, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-07T16:00:20.235804"}
+{"mean_reward": 16.9, "std_reward": 6.920260110718383, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-07T16:42:11.198623"}