Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 18.20 +/- 14.05
+      value: 60.10 +/- 45.53
       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": 128, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.9, "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 sha256:7950cefe3ba8d31b8334e9ef55ccbb51989c4e035b3beae3f9da071d99058472
-size 105467
+oid sha256:c2cdefbe2848b7ecd51c61bdb25203350a6ba84765bd5f013461494bf0ca0f96
+size 404539

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 18.2, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-13T17:29:04.946486"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 60.1, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-13T20:10:02.693884"}