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: 198.50 +/- 107.32
+      value: -135.88 +/- 72.54
       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
-  {'f': '/root/.local/share/jupyter/runtime/kernel-5b793a8d-4b38-4d26-8f74-20bef15c398e.json'
+  {'f': '/root/.local/share/jupyter/runtime/kernel-dac0e9f5-784f-4f8d-aef1-b45f763f07da.json'
 'exp_name': 'test1'
 'seed': 1
 'torch_deterministic': True
@@ -36,8 +36,8 @@ model-index:
 'track': False
 'wandb_project_name': 'cleanRL'
 'wandb_entity': None
-'capture_video': False
-'env_id': 'CartPole-v1'
+'capture_video': True
+'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4

logs/events.out.tfevents.1683202790.9615339ccea0.887.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46255199db3103ddffe51a1c1e0912b4de9e015d3076f543125062ae77642fbf
+size 110063

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2696e0cd90c2a51c12b41eb83e89a403053d0d874e11feec409c33eb1f196a3a
-size 40037
+oid sha256:5a363dfe098933c96feb65ea5062a91e8aacf7448c05ac211c1404fb4e0f78d9
+size 42597

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 198.5, "std_reward": 107.3212467314837, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-04T10:42:34.857668"}
+{"env_id": "LunarLander-v2", "mean_reward": -135.87574430448478, "std_reward": 72.54308755155596, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-04T12:20:51.559993"}