Push agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- CartPole-v1
+- LunarLander-v2
 - ppo
 - deep-reinforcement-learning
 - reinforcement-learning
@@ -13,18 +13,18 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: CartPole-v1
-      type: CartPole-v1
+      name: LunarLander-v2
+      type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 205.60 +/- 69.11
+      value: -159.69 +/- 130.26
       name: mean_reward
       verified: false
 ---
 
-  # PPO Agent Playing CartPole-v1
+  # PPO Agent Playing LunarLander-v2
 
-  This is a trained model of a PPO agent playing CartPole-v1.
+  This is a trained model of a PPO agent playing LunarLander-v2.
     
   # Hyperparameters
   ```python
@@ -36,7 +36,7 @@ model-index:
 'wandb_project_name': 'cleanRL'
 'wandb_entity': None
 'capture_video': False
-'env_id': 'CartPole-v1'
+'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4

logs/events.out.tfevents.1747893621.20967575cbd7.22105.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea3b30d47be2f2bfcd32e322056340570073b83a248af85d1c98e578243b9230
+size 110093

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbd16babc963802f3a659e2dd9d811e8388faf60e12e9d17635e4589fb103e41
-size 40466
+oid sha256:339f09e8b06f686b9c10d26099e14e7a7303e9b6ecce9f9f6a67b3d5b02b6551
+size 43026

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 205.6, "std_reward": 69.11034654811101, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-22T05:34:06.255898"}
+{"env_id": "LunarLander-v2", "mean_reward": -159.6887733546949, "std_reward": 130.25933029063395, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-22T06:01:03.515714"}