Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -168.87 +/- 74.30
+      value: -195.63 +/- 130.47
       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'
@@ -52,7 +52,7 @@ model-index:
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5
-'max_grad_norm': 0.5
+'max_grad_norm': 0.1
 'target_kl': None
 'repo_id': 'DavidCollier/ppo-LunarLander-v2-unit8'
 'batch_size': 512

logs/events.out.tfevents.1704518781.cef9efba8278.4000.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e39d6e745fdc3ddf9363b0d9b96f26a0b66ba5eb4e136a718f68755a7d764b9a
+size 111589

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
+oid sha256:2e86dd2d772bb64dab603961cc1e67d2946573be40a6686deb93304bc57f3e32
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -168.86857957820206, "std_reward": 74.29628684453124, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-06T04:34:59.545300"}
+{"env_id": "LunarLander-v2", "mean_reward": -195.62968173794079, "std_reward": 130.47289936567753, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-06T05:27:06.627106"}