Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -1555.86 +/- 2779.71
+      value: 135.90 +/- 133.79
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 1000000
-'learning_rate': 0.025
+'learning_rate': 0.0025
 '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': 0.01
-'vf_coef': 0.5
+'ent_coef': 0.02
+'vf_coef': 0.3
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'hartman23/ppo-LunarLander-v2'

logs/events.out.tfevents.1736802762.ebc41fb37504.9499.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c58bb1b7d8187887bb3c4b635ac1452a4546a76fac49a673861cbd78835c0c8
+size 1519749

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c331d1fb35daeb3fd34135eef6cc515240a6edf3e0c140b0890f3ab34791eb4d
+oid sha256:dc93bf12d99d9805d23bbfc1215c99780e1c0929c7c3e9d0e1d2939faa3e9a33
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -1555.8568090329893, "std_reward": 2779.706929395287, "n_evaluation_episodes": 10, "eval_datetime": "2025-01-13T21:08:55.948459"}
+{"env_id": "LunarLander-v2", "mean_reward": 135.89665841907333, "std_reward": 133.79059109628892, "n_evaluation_episodes": 10, "eval_datetime": "2025-01-13T21:29:37.148480"}