Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 18.57 +/- 16.91
+      value: 22.16 +/- 21.10
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 50000, "n_evaluation_episodes": 100, "max_t": 30000, "gamma": 0.99, "lr": 0.0003, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 128, "n_training_episodes": 50000, "n_evaluation_episodes": 100, "max_t": 30000, "gamma": 0.99, "lr": 0.0002, "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 sha256:60f980cd806565cd550bbdb3bf8533483af0bccadb7c121da49fba6732a205fe
-size 38983
+oid sha256:289c2829bbfc2a71976755baa63179e5e8034849598ee6ec8568f6c71ab1a294
+size 140871

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 18.57, "n_evaluation_episodes": 100, "eval_datetime": "2023-02-07T22:12:14.073694"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 22.16, "n_evaluation_episodes": 100, "eval_datetime": "2023-02-07T23:32:18.027750"}