Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 44.50 +/- 25.90
+      value: 30.20 +/- 22.72
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"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}
+{"h_size": 64, "n_training_episodes": 25000, "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:ca6fc2196311e26354500a16617f4dd94f01a2ff33da3b3416ecb4107e2a42f6
+oid sha256:1c0a7d78f4077ced307e0f65153edff9da39bb021b9b51e5b8719e65b6a534b6
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 44.5, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-13T03:53:46.506198"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 30.2, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-13T05:37:30.598937"}