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: 185.10 +/- 54.49
+      value: -142.34 +/- 101.55
       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.1697272206.aa31f9ed222e.9005.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47c3e804bab2305bb74939463ef2b2d3a0ce151640a5a95a701f8f5cb14d1993
+size 109713

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c1385a7a78751dbc256d42b613d77d87fbbd3e2457ed856b229209a56255872
-size 40037
+oid sha256:c706c81696f37ceaeb74d41e1262ec54c4e2f63b8cbb791c8b01decf796f6a53
+size 42597

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 185.1, "std_reward": 54.49486214314153, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-14T08:25:59.199791"}
+{"env_id": "LunarLander-v2", "mean_reward": -142.34443694625614, "std_reward": 101.55478173138404, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-14T08:30:53.303273"}