Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: -2.50 +/- 0.50
+      value: 58.40 +/- 38.24
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 128, "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": 32, "n_training_episodes": 20000, "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 sha256:3984a947d0d386a767add96b52b47c442283f250dd27b91d7a67c4fd61757352
-size 930927
+oid sha256:267369a5b38b6489a172cdff6a6be424b4a3fa13a1eb19b35449f0b6ef684277
+size 63471

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -2.5, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-15T07:53:30.589374"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 58.4, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-15T12:36:33.483933"}