Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -13.18 +/- 76.97
+      value: -130.16 +/- 80.59
       name: mean_reward
       verified: false
 ---
@@ -38,19 +38,19 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 500000
-'learning_rate': 0.00025
+'learning_rate': 2.5e-05
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
+'gamma': 0.98
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.01
+'ent_coef': 0.02
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None

logs/events.out.tfevents.1689762943.928328e29417.20376.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a629b1cb9143c3472cbde24d843a47cbce5182a96fc8c5a9fcde5fbcfb3b79f2
+size 1054807

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95d2db815a33646e84e478628a4da4f156c95480a7b55276eebdc219ec4fcd18
+oid sha256:5e60a82827317b4fd1e1d0e0d8da7fb2f9d22f84c75f1b9f7bd4b7c2a1e09ed9
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -13.181073781331534, "std_reward": 76.9688355392384, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-19T10:17:30.319249"}
+{"env_id": "LunarLander-v2", "mean_reward": -130.15867781916094, "std_reward": 80.59419966390114, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-19T10:42:47.191818"}