Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 135.90 +/- 133.79
+      value: 266.19 +/- 24.05
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
-'learning_rate': 0.0025
+'total_timesteps': 5000000
+'learning_rate': 0.005
 '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': 0.02
-'vf_coef': 0.3
+'ent_coef': 0.001
+'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'hartman23/ppo-LunarLander-v2'

logs/events.out.tfevents.1736873879.aa8ec514f65f.2138.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a6aa47750bdb12c9900c230f41bf12e76bd88f8e64befba451e4d5de8de60b7
+size 7315189

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc93bf12d99d9805d23bbfc1215c99780e1c0929c7c3e9d0e1d2939faa3e9a33
-size 43026
+oid sha256:963432b502783d156cb34482cc5007bcf2e1a438ce2c99118eabf5627c066329
+size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 135.89665841907333, "std_reward": 133.79059109628892, "n_evaluation_episodes": 10, "eval_datetime": "2025-01-13T21:29:37.148480"}
+{"env_id": "LunarLander-v2", "mean_reward": 266.1900668069389, "std_reward": 24.054309436584514, "n_evaluation_episodes": 10, "eval_datetime": "2025-01-14T18:40:01.948298"}