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: 169.70 +/- 34.72
+      value: -124.76 +/- 59.24
       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.1679678767.akriel-B450-AORUS-ELITE.84324.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33bacecab4749d2f96d5822aa14769c6129814a2f0372645716ed861d1535a91
+size 111156

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88859a7c3ccd409ea1c47ddabc18ba815a33985af64b4a6519ba870c03775e44
-size 40037
+oid sha256:65320413a314be724a72485c454ccf583218af1dcf90912168855519ab09640d
+size 42597

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 169.7, "std_reward": 34.72477501726973, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-24T19:25:08.885753"}
+{"env_id": "LunarLander-v2", "mean_reward": -124.75512509808217, "std_reward": 59.24447072761277, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-24T19:26:43.435969"}