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: 26.10 +/- 14.19
+      value: -89508.36 +/- 3533.16
       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.1728240743.dunhill.sot.com.453333.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc46d6454402250476db5d1026cf96c94593077aeeabc46b0a79228346e54b15
+size 110113

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c497f9c697ee77143486901a2749196878379ccd4821855a7230fd5b936a113
-size 40338
+oid sha256:dca41d73c4754fbb8e396a2db8453a9e917fc5a6648a9a75d6e1a8791ab8f333
+size 42898

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 26.1, "std_reward": 14.194717327231283, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-06T21:33:38.799739"}
+{"env_id": "LunarLander-v2", "mean_reward": -89508.36303979004, "std_reward": 3533.1601373755657, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-06T21:53:06.200811"}