Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 11.90 +/- 11.44
+      value: 54.70 +/- 37.65
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 30000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 1e-05, "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 sha256:196e84fdb6e6bc373e700d2348d6ea82ade91d075258a35f06f3b335be18d64d
+oid sha256:b0fd8d259e7e0a1706ab4e6504d9b1acd840f6271c6b34cca5823741fc2d9ced
 size 39239

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 11.9, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-05T15:44:18.000201"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 54.7, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-11T11:24:28.503158"}