Push agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- LunarLander-v2
+- CartPole-v1
 - ppo
 - deep-reinforcement-learning
 - reinforcement-learning
@@ -13,18 +13,18 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: LunarLander-v2
-      type: LunarLander-v2
+      name: CartPole-v1
+      type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: -143.51 +/- 92.11
+      value: 210.20 +/- 56.48
       name: mean_reward
       verified: false
 ---
 
-  # PPO Agent Playing LunarLander-v2
+  # PPO Agent Playing CartPole-v1
 
-  This is a trained model of a PPO agent playing LunarLander-v2.
+  This is a trained model of a PPO agent playing CartPole-v1.
     
   # Hyperparameters
   ```python
@@ -36,7 +36,7 @@ model-index:
 'wandb_project_name': 'cleanRL'
 'wandb_entity': None
 'capture_video': False
-'env_id': 'LunarLander-v2'
+'env_id': 'CartPole-v1'
 'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4

logs/events.out.tfevents.1677520655.60531b5d1450.25248.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2125f2149c5eb576bc170cb5e635cc31051bb09eaf4801fd768f4036b9abc3fb
+size 106879

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0762c60b8952f57601a85c2d5d3d6f6e862f4cc07ba530b06e3bd7b2d806a2a3
-size 42597
+oid sha256:7d09977aa0ea3286a5b32a76ad724d81f6c0562af591871d161460dadc42e2a3
+size 40037

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -143.50532741125676, "std_reward": 92.11305038109163, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-27T17:54:45.086191"}
+{"env_id": "CartPole-v1", "mean_reward": 210.2, "std_reward": 56.47796030311293, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-27T17:58:11.478241"}