Upload . with huggingface_hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 5.80 +/- 4.31
+      value: 45.10 +/- 39.04
       name: mean_reward
     task:
       type: reinforcement-learning

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 1000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 64, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46454ffc528cfb8a89a29d7a7c7682e2c15489266f5f6ed8864c0ff0a1764889
+oid sha256:e5650d38ff955b59e81a9f57fd948815d462f207c48db8e3b479495d0ba6c7a6
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 5.8, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-06T19:34:59.610045"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 45.1, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-06T21:48:49.031902"}