Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -58.07 +/- 70.52
+      value: -45.92 +/- 30.02
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 200000
-'learning_rate': 0.0003
+'learning_rate': 0.01
 'num_envs': 8
 'num_steps': 1024
 'anneal_lr': True
@@ -48,7 +48,7 @@ model-index:
 'num_minibatches': 16
 'update_epochs': 8
 'norm_adv': True
-'clip_coef': 0.1
+'clip_coef': 0.3
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1716228610.9fcd669d44f2.8730.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03dfa5db51eb7b0d967b3ce4e46586f807c8b4f4efde586c523f3d8abdff3ccc
+size 105387

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f3e8d25fe31b882371ac566e65a6d1e7235295b6d79118d4ee29527c9084d27
+oid sha256:291950b676b293bedced1092628ca4b2dece9caeaf9ba411eae5256bd8d8b2fe
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -58.069497490159605, "std_reward": 70.51645279748034, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-20T18:06:13.518684"}
+{"env_id": "LunarLander-v2", "mean_reward": -45.91577468307116, "std_reward": 30.02360801769363, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-20T18:14:48.183138"}