Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 8.30 +/- 6.87
+      value: 36.80 +/- 25.61
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 5000, "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": 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}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cef63eeffeeed12542660b8b399c8c060425331fb5ac71491aa739d732fa8a14
+oid sha256:c10f2929fa116d19eeaeb52c0aedfcc7e4df427ab4d59c7612d6ba59f98b851a
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 8.3, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-28T17:41:06.726711"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 36.8, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-28T21:37:35.456920"}