Push Reinforce agent to the Hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 157.60 +/- 28.70
+      value: 87.10 +/- 23.55
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 5000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.98, "lr": 0.001, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}
+{"h_size": 16, "n_training_episodes": 5000, "n_evaluation_episodes": 10, "max_t": 20000, "gamma": 0.98, "lr": 0.001, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d32853245589aae5406349dde1f79c1a866fc514115430041a5359c4eb43786
-size 3935
+oid sha256:b96d7ec27c971e2a63cb195f21047bafd59a761e6eafd9b585a8befa69e2fdcc
+size 4183

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c477725f06f74971d71cad5b3dd72b3b0d19ec5798a47fc00d32db83fd0b841f
-size 23708
+oid sha256:255d94f9026bd1336b064062046c7670f75d1215bbda5807825b366f363c5225
+size 11925

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 157.6, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-03T13:38:19.120134"}
+{"env_id": "CartPole-v1", "mean_reward": 87.1, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-03T13:57:51.398203"}