Initial commit

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 260.00 +/- 0.00
+      value: 2.00 +/- 0.00
       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:e715a1736b9e86d98c255626e33d1d2c2ae67f6ac0056efde7ad05b7f06e30e3
-size 342202601
+oid sha256:01afe793b7a45e279cb63133e6c9eb394fc986e2c602475b03aba8c7fcf0926a
+size 13707008

a2c-CartPole-v1/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb271ea29db16612f492bcc186d53c5c83e6b69588fbf6b1d3221e88bf12f85a
-size 227166841
+oid sha256:7675208fcacac3de01a03dc7bdc5229acfce355f0510a6d91696264206188c8f
+size 6750209

a2c-CartPole-v1/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e8f09092c2dab1d0a8b2a5d2a895e5ef95914c99aa138743452515c200c5932
-size 113582785
+oid sha256:2c181243e15910246de36b026323ff9cc6038cdefd53890be3c08d24236db0e7
+size 6750913

results.json

@@ -1 +1 @@
-{"mean_reward": 260.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-07T04:31:33.388894"}
+{"mean_reward": 2.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-07T14:38:36.595854"}