Upload folder using huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 4.50 +/- 3.50
+      value: 8.40 +/- 9.38
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 10000, "n_evaluation_episodes": 2, "max_t": 10000, "gamma": 0.9, "lr": 8e-05, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 64, "n_training_episodes": 15000, "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:bd1db34c823631917ceb96eba5b0a332720cbe4dea0f7a9b3f5b14244124cee8
-size 39732
+oid sha256:0dd74113b60721cdf5cc9b2a36174cc2a650488af7e017ef570b06581dfcf2fe
+size 39668

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 4.5, "n_evaluation_episodes": 2, "eval_datetime": "2024-05-21T11:38:38.111325"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 8.4, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-21T13:28:09.055298"}