Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 18.10 +/- 14.22
+      value: 42.20 +/- 29.12
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 32, "n_training_episodes": 20000, "n_evaluation_episodes": 10, "max_t": 20000, "gamma": 0.99, "lr": 0.0005, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 64, "n_training_episodes": 30000, "n_evaluation_episodes": 10, "max_t": 30000, "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 sha256:40fa363252a04dfc8292797d277a96e95be9257f6b19d936de50ec9d1ab87d10
-size 12615
+oid sha256:60e582b8015bb2c6cd0626fc18dcf74bc426017b953db624737c09ea4ff48e54
+size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 18.1, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-06T20:31:16.704312"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 42.2, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-06T22:11:43.608268"}