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 +/- 57.33
+      value: -147.02 +/- 83.53
       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.1676805884.ad1a63371cd3.20372.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9ed49f15965a70e8bf01bb0f84ed680dfda5118d3463c617f1ea1afbca3070b
+size 111706

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c183fcfe913192f9c6c37ffedf74d02e114d065710cd4d89eba5a6e393ffa132
-size 39909
+oid sha256:1cd0ac613a3793f26156783acd591c2a308e94a91d78575d5ceabd812fab4370
+size 42469

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 185.1, "std_reward": 57.33489338962792, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T11:13:46.044102"}
+{"env_id": "LunarLander-v2", "mean_reward": -147.02385699881663, "std_reward": 83.52639839101187, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T11:25:17.133887"}