Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -73.56 +/- 35.52
+      value: -29.00 +/- 34.39
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 300000
-'learning_rate': 0.0005
+'total_timesteps': 200000
+'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
@@ -50,8 +50,8 @@ model-index:
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.005
-'vf_coef': 0.25
+'ent_coef': 0.01
+'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'earlzero/LunarLander-CleanRL'

logs/events.out.tfevents.1735412205.2763f7ab14bb.11026.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11481f681dadfa93505066311be4f2e7fcc58aecaea96b3b6c3370c4be748403
+size 342324

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:282313172ed1676e84e50f1652b45d3c455b4675045e6c308468f8cae913ce7e
+oid sha256:4ccce4430cd2484cb7e2271f5e70f49147c1e0fa609462c182399fdfbd028f05
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -73.56140479922956, "std_reward": 35.52134750209078, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-28T18:55:19.634480"}
+{"env_id": "LunarLander-v2", "mean_reward": -28.995675383970166, "std_reward": 34.38629337148058, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-28T19:00:26.799570"}