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: 200.10 +/- 115.47
+      value: -143.96 +/- 103.63
       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.1717708584.832600f03a47.11505.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb1ea30e9c647ea297c01e739421eaa7110fd8fb0242eecf5975ef2951b2b12
+size 110091

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07d38f85015109181b62f1488dbb4d4315b6e359bf697709ae2b8e98ab701cdc
-size 40466
+oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
+size 43026

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 200.1, "std_reward": 115.46986619893521, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-06T21:12:44.757013"}
+{"env_id": "LunarLander-v2", "mean_reward": -143.95573362146115, "std_reward": 103.62834360969167, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-06T21:17:13.310864"}