Push agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- CartPole-v1
+- LunarLander-v3
 - 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-v3
+      type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 172.80 +/- 54.60
+      value: -194.66 +/- 56.22
       name: mean_reward
       verified: false
 ---
 
-  # PPO Agent Playing CartPole-v1
+  # PPO Agent Playing LunarLander-v3
 
-  This is a trained model of a PPO agent playing CartPole-v1.
+  This is a trained model of a PPO agent playing LunarLander-v3.
 
   # 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-v3'
 'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4

logs/events.out.tfevents.1745998595.1c54943520c2.688.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f74e8597e0f1db20e3e958b4c9cf10712e96c83d438015a1407f3f9135a20b2d
+size 302507

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbd16babc963802f3a659e2dd9d811e8388faf60e12e9d17635e4589fb103e41
-size 40466
+oid sha256:6414dd2e4bdb9a97f3b5a6089aed8b832856aed901830a3316d4d0a68db42da6
+size 43026

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 172.8, "std_reward": 54.59633687345699, "n_evaluation_episodes": 10, "eval_datetime": "2025-04-30T07:13:08.335770"}
+{"env_id": "LunarLander-v3", "mean_reward": -194.66023647192617, "std_reward": 56.221235899874316, "n_evaluation_episodes": 10, "eval_datetime": "2025-04-30T07:37:09.920896"}