Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 10.42 +/- 8.78
+      value: 33.25 +/- 25.02
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 10000, "n_evaluation_episodes": 12, "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": 12, "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:f44d5aaae8c9465053980a80bfafa236441c44203adf36e2a2eb915cdc980615
+oid sha256:9112c133d786f21ae9021e5cb29e4f8c2eb9698d40df8f6fc061ff611ef8e16f
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 10.416666666666666, "n_evaluation_episodes": 12, "eval_datetime": "2023-01-25T14:00:05.281162"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 33.25, "n_evaluation_episodes": 12, "eval_datetime": "2023-01-25T16:44:31.412331"}