Upload . with huggingface_hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 61.24 +/- 25.07
+      value: 490.19 +/- 66.02
       name: mean_reward
     task:
       type: reinforcement-learning

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 16, "n_training_episodes": 100, "n_evaluation_episodes": 100, "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": 1200, "n_evaluation_episodes": 100, "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:ef919db643b0ff2ab197dcf7b306f2e3cd35198d9da3c14961f61d869b64a32f
+oid sha256:c87ee01b03dcf813c88d8e7149ea17b3cf151873fb7f9a77757eb617a862d0f9
 size 2771

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 61.24, "n_evaluation_episodes": 100, "eval_datetime": "2023-07-09T17:31:26.286427"}
+{"env_id": "CartPole-v1", "mean_reward": 490.19, "n_evaluation_episodes": 100, "eval_datetime": "2023-07-09T17:50:49.936496"}