Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 11.40 +/- 14.81
+      value: 40.40 +/- 21.33
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 128, "n_training_episodes": 10000, "n_evaluation_episodes": 10, "max_t": 15000, "gamma": 0.8, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 128, "n_training_episodes": 20000, "n_evaluation_episodes": 10, "max_t": 15000, "gamma": 0.95, "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:b49ad9a62aeacd413581ef175aafd9befaf56e26672cc6b1df7c851f1e531342
+oid sha256:2cbf2254bd8335d43f3273108eb8a3b3c249a1f9daeb45785bd7b990537234e5
 size 73799

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 11.4, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-23T19:19:27.930343"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 40.4, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-24T05:12:48.546461"}