Push agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- CartPole-v1
+- LunarLander-v2
 - ppo
 - deep-reinforcement-learning
 - reinforcement-learning
@@ -13,19 +13,19 @@ 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: 254.00 +/- 124.01
+      value: -177.37 +/- 85.15
       name: mean_reward
       verified: false
 ---
 
-  # PPO Agent Playing CartPole-v1
-
-  This is a trained model of a PPO agent playing CartPole-v1.
+  # PPO Agent Playing LunarLander-v2
 
+  This is a trained model of a PPO agent playing LunarLander-v2.
+    
   # Hyperparameters
   ```python
   {'exp_name': 'ppo'
@@ -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.1680796520.8d593442c7ec.4040.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecccebc69132fada3d0cd071c90dbe9033eb35d852e873c4383257079001070b
+size 109965

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3585dd9f67771c9d2d9cc79cae73f556cf671b9076ed444c6d23f82e23a9c27c
-size 39909
+oid sha256:fb1e581e8ea089e394de546be12d511004e2bf415ffa041b3a747b063f4a10bc
+size 42597

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 254.0, "std_reward": 124.01290255453262, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-06T17:32:10.537438"}
+{"env_id": "LunarLander-v2", "mean_reward": -177.37114091008803, "std_reward": 85.14679528417939, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-06T15:56:11.546244"}