Push Reinforce agent to the Hub

README.md

@@ -9,16 +9,17 @@ tags:
 model-index:
 - name: PPO
   results:
-  - metrics:
-    - type: mean_reward
-      value: 166.00 +/- 55.22
-      name: mean_reward
-    task:
+  - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
       name: CartPole-v1
       type: CartPole-v1
+    metrics:
+    - type: mean_reward
+      value: 191.60 +/- 75.81
+      name: mean_reward
+      verified: false
 ---
 
   # PPO Agent Playing CartPole-v1
@@ -54,7 +55,6 @@ model-index:
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
-'virtual_display': True
 'repo_id': 'NithirojTripatarasit/ppo-CartPole-v1'
 'batch_size': 512
 'minibatch_size': 128}

logs/events.out.tfevents.1662593036.c631b7690fa4.883.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16283c1c5c6bc40acf78a96282d588897351c2d3509e8f6220c69eaa6c7267d8
+size 50365

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:615063e1c901e83f6483e95e25739786a9c37a58a7e03e55a1c56f95f7e1493a
-size 40129
+oid sha256:befd74b53822918297bf329aeeada1b79a74d407ba3283356a68f6d4df52648a
+size 40257

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 166.0, "std_reward": 55.22499434133063, "n_evaluation_episodes": 10, "eval_datetime": "2022-09-08T05:38:57.571085"}
+{"env_id": "CartPole-v1", "mean_reward": 191.6, "std_reward": 75.81187242114522, "n_evaluation_episodes": 10, "eval_datetime": "2022-09-07T23:24:28.838257"}