Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 23.70 +/- 14.22
+      value: 105.30 +/- 132.52
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 80, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 15000, "gamma": 0.999, "lr": 5e-05, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 70, "n_training_episodes": 65000, "n_evaluation_episodes": 10, "max_t": 15000, "gamma": 0.95, "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 sha256:9018b2c168bb340edaef8ded19ee53e8df72107d38e95991e6b37c5f7ab59e00
-size 58311
+oid sha256:10cfe6d13200bd2ddbc71cc34268dba278f52a3be17148355a192e6e70af259a
+size 85435

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 23.7, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-08T18:42:14.997537"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 105.3, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-09T04:05:04.803887"}