Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -132.31 +/- 78.10
+      value: -164.89 +/- 105.61
       name: mean_reward
       verified: false
 ---
@@ -25,7 +25,7 @@ model-index:
   # PPO Agent Playing LunarLander-v2
 
   This is a trained model of a PPO agent playing LunarLander-v2.
-    
+
   # Hyperparameters
   ```python
   {'exp_name': 'ppo'
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 5000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1685524219.alex-pc.8589.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d8c8be900832ab7df549963dee30112435c709aaedcee6a7c04a33ab17fe447
+size 10890

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba9eba95178b8c1eeff91f1866f65cb2c8b1c65ceedc704e4da139555fb0614
-size 42597
+oid sha256:5d039f132914d087d7ca0c814b9d0de3992702a7c654ee15418c26919e7b96b4
+size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -132.3147405187181, "std_reward": 78.10182626884038, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-31T08:59:08.406390"}
+{"env_id": "LunarLander-v2", "mean_reward": -164.88952286139113, "std_reward": 105.61030070415077, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-31T12:10:23.076887"}