Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 90.90 +/- 104.36
+      value: 16.90 +/- 7.45
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 100000, "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": 32000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.9992758781945783, "lr": 9.787191026358761e-05, "env_id": "Pixelcopter-PLE-v0", "state_space": 16, "action_space": 2}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a0b6e5ba130876646161e72bfe73600eca70977713a008405d9f945da824263
-size 71931
+oid sha256:2191271f1192282b991a53a10f58df95dbca0a793816d5f51c6cbdf2a82cacc3
+size 58491

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 90.9, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-12T12:15:57.568813"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 16.9, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-13T16:19:30.448499"}