Upload folder using huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 92.57 +/- 33.12
+      value: 225.11 +/- 68.16
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 20000, "n_evaluation_episodes": 10, "max_t": 500, "gamma": 0.995, "lr": 0.001, "env_id": "LunarLander-v2", "state_space": 8, "action_space": 4}
+{"h_size": 64, "n_training_episodes": 5000, "n_evaluation_episodes": 10, "max_t": 500, "gamma": 0.995, "lr": 0.001, "env_id": "LunarLander-v2", "state_space": 8, "action_space": 4}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b73aaffb73d972fa9666664b1b413119759e0586144d73be0ba13efbbd8d9a3b
+oid sha256:649a4c4344154a785aa623eaeef9f12b44825d664797b3f28b400180d78f03b0
 size 41012

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 92.56536495891059, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-11T00:02:54.577216"}
+{"env_id": "LunarLander-v2", "mean_reward": 225.1133021695594, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-11T02:06:34.885688"}