Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -124.84 +/- 88.47
+      value: -150.42 +/- 64.87
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 80000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
@@ -50,7 +50,7 @@ model-index:
 'norm_adv': True
 'clip_coef': 0.1
 'clip_vloss': True
-'ent_coef': 0.02
+'ent_coef': 0.01
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None

logs/events.out.tfevents.1745976818.59b34e00c18a.11872.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:166af59619a9d5f5a8760cf159b82e743d099f05626dfb2a32866c5c55a215ac
+size 177440

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fcc60b3b92b7c0d95ae4a392fc4f6cabc87356f130581b185d99de46dccf602
+oid sha256:24dc0a527ab2a596602458d68ae9dbc4ebf3b0e5bbbb953ff14398f9e6787df1
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -124.84232256435561, "std_reward": 88.46827031320791, "n_evaluation_episodes": 10, "eval_datetime": "2025-04-30T01:32:01.503689"}
+{"env_id": "LunarLander-v2", "mean_reward": -150.42208756762867, "std_reward": 64.86621057909801, "n_evaluation_episodes": 10, "eval_datetime": "2025-04-30T01:34:36.059590"}