Push Reinforce agent to the Hub

README.md

@@ -9,17 +9,16 @@ tags:
 model-index:
 - name: PPO
   results:
-  - task:
+  - metrics:
+    - type: mean_reward
+      value: 208.80 +/- 135.81
+      name: mean_reward
+    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
@@ -55,6 +54,7 @@ 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.1662596434.nt-pc.12406.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c6baaa6993323c811c08e20722d9636a43be51e7f68f7d82aa65305806538c8
+size 116432

model.pt

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

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 191.6, "std_reward": 75.81187242114522, "n_evaluation_episodes": 10, "eval_datetime": "2022-09-07T23:24:28.838257"}
+{"env_id": "CartPole-v1", "mean_reward": 208.8, "std_reward": 135.81369592202398, "n_evaluation_episodes": 10, "eval_datetime": "2022-09-08T07:21:02.945543"}