Upload folder using huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 186.44 +/- 50.78
+      value: -8.86 +/- 68.90
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 10000, "n_evaluation_episodes": 10, "max_t": 500, "gamma": 0.999, "lr": 0.001, "env_id": "LunarLander-v2", "state_space": 8, "action_space": 4}
+{"h_size": 64, "n_training_episodes": 2000, "n_evaluation_episodes": 10, "max_t": 250, "gamma": 0.99, "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 sha256:41cb14b711bc5348ec9992cb6adf5bdec382e725e094f2b67c6b4e74dcb7f8a2
+oid sha256:cf4cf64367ab093717977a5d065b109a33fcec5673f614cfd51d73ead8f55231
 size 41012

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 186.4414530242853, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-11T03:49:51.654951"}
+{"env_id": "LunarLander-v2", "mean_reward": -8.85631804802474, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-11T12:30:44.324186"}