PushReinforceagenttotheHub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 185.80 +/- 11.56
+      value: 93.20 +/- 24.82
       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": 5000, "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 sha256:16b5e3b17d5978d6d212443a3cb2c5af3e56475f30576043465b71f1ce91a8b5
+oid sha256:f952099e6564c40721fa0f232a3b5adc91f35e86a6dd2ebc399800698e2ff5c1
 size 2591

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e2584d49ac8551198e489c42e2ba449195538c8ab4bfef5d53ea7d8f205fd99
-size 23717
+oid sha256:ad404889f0fde481d5f8559444793aa236942619acbac36a04a7efb7f02a987a
+size 15400

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 185.8, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-25T20:48:56.166853"}
+{"env_id": "CartPole-v1", "mean_reward": 93.2, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-25T21:10:47.993849"}