Upload folder using huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -8.86 +/- 68.90
+      value: 46.08 +/- 50.78
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"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}
+{"h_size": 64, "n_training_episodes": 2000, "n_evaluation_episodes": 10, "max_t": 250, "gamma": 0.999, "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:cf4cf64367ab093717977a5d065b109a33fcec5673f614cfd51d73ead8f55231
+oid sha256:15a36ee658b6f15c440590cdde1ff7ba66c4431448331cce848c61ff7a6bafbf
 size 41012

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -8.85631804802474, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-11T12:30:44.324186"}
+{"env_id": "LunarLander-v2", "mean_reward": 46.08053885641963, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-11T13:06:20.846623"}