Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -28.50 +/- 39.32
+      value: 51.12 +/- 118.12
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 200000
+'total_timesteps': 2000000
 'learning_rate': 0.0001
 'num_envs': 8
 'num_steps': 256
@@ -53,7 +53,7 @@ model-index:
 'ent_coef': 0.01
 'vf_coef': 0.5
 'max_grad_norm': 0.5
-'target_kl': None
+'target_kl': 0.01
 'repo_id': 'SyNgu/ppo.py'
 'batch_size': 2048
 'minibatch_size': 256}

logs/events.out.tfevents.1731513788.6aadb1a1c030.4824.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cba52624623e7c96397c628520b3ca80ba0d695aa3d6b03fb6587004ae110f7d
+size 936607

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d79d8e106292739e0bc655cc74ff8a91653c885db3a998afc415852a811b5770
+oid sha256:8510ed89631f960b97c1513543160596122b4ca00e122d1c89dd6005ba161fa2
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -28.50138137480595, "std_reward": 39.31765556489808, "n_evaluation_episodes": 10, "eval_datetime": "2024-11-12T16:17:39.649315"}
+{"env_id": "LunarLander-v2", "mean_reward": 51.12038653745542, "std_reward": 118.11572840732448, "n_evaluation_episodes": 10, "eval_datetime": "2024-11-13T16:48:36.158249"}