Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 25.80 +/- 22.31
+      value: 45.30 +/- 41.85
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 20000, "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": 132, "n_training_episodes": 25000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.97, "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:fa11459f8a73e7c607243789514eddc05de82cb3e0d766bc48e3039b0df91dcd
-size 38983
+oid sha256:33b1e42b2d02deb909f0ffd07c01fc4ae84405ccbfd7e7257b60be8511f2a032
+size 149511

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 25.8, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-13T14:47:11.245230"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 45.3, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-13T16:14:51.090008"}