Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: -5.00 +/- 0.00
+      value: 23.60 +/- 20.54
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 10000, "n_evaluation_episodes": 17, "max_t": 12099, "gamma": 0.9812066943892069, "lr": 0.005931060514432652, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 128, "n_training_episodes": 50000, "n_evaluation_episodes": 15, "max_t": 10000, "gamma": 0.99, "lr": 0.000170377831182511, "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:c12d0eed106b9a64a317f273d3a1987655c21b77ceb7b525c05692e026ab02f2
-size 38919
+oid sha256:e1eceb0d211f6bcc78d4e81180bddc427c2201014b579e7b02cdbada0b1f75eb
+size 140807

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -5.0, "n_evaluation_episodes": 17, "eval_datetime": "2023-01-10T12:46:09.560416"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 23.6, "n_evaluation_episodes": 15, "eval_datetime": "2023-01-10T23:14:25.924465"}