Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 99.50 +/- 20.98
+      value: 500.00 +/- 0.00
       name: mean_reward
     task:
       type: reinforcement-learning

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 16, "n_training_episodes": 1000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 1.0, "lr": 0.01, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}
+{"h_size": 16, "n_training_episodes": 10000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 1.0, "lr": 0.01, "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:f1d9351062a5dcc513714286db227930219c27fe0b4c20ce12e6e7f1a46e82d4
+oid sha256:831e9691cb8432cc8a45412c9434cd915ea4fe2330fed7c7eb73251ff47cdfd5
 size 2527

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b05264433cced2b0eb9df769d72074cd4767cff6f17d86aa90a6db4fffb4f846
-size 12176
+oid sha256:ba086d114325d4f918f4b41718a1360393791bb4d0014cd89998557876ded2ec
+size 41915

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 99.5, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-06T12:59:19.364016"}
+{"env_id": "CartPole-v1", "mean_reward": 500.0, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-06T13:38:37.200334"}