Push agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- CartPole-v1
+- LunarLander-v2
 - ppo
 - deep-reinforcement-learning
 - reinforcement-learning
@@ -13,22 +13,22 @@ 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: 201.30 +/- 76.86
+      value: -139.39 +/- 59.56
       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
-  {'exp_name': 'ppo_test'
+  {'exp_name': 'ppo_experiment'
 'seed': 1
 'torch_deterministic': True
 'cuda': True
@@ -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.1750916303.d9b51d3183e0.24608.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f582bcc42e95ec344ddc7521cdb92ec38b577b4f5869dde3a30391c324e8ad9
+size 109738

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:253f0e4b6304f0dc7378e7ccc2960aa8eaace3a0185975f83d3c3cb9877e6234
-size 40466
+oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
+size 43026

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 201.3, "std_reward": 76.86488144790181, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-24T06:41:22.521043"}
+{"env_id": "LunarLander-v2", "mean_reward": -139.3899894995028, "std_reward": 59.55686224378976, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-26T05:39:04.220327"}