Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -112.91 +/- 61.09
+      value: -95.72 +/- 18.04
       name: mean_reward
       verified: false
 ---
@@ -39,7 +39,7 @@ model-index:
 'f': '/root/.local/share/jupyter/runtime/kernel-034b7df4-145b-4db4-9d09-b6d875ced33d.json'
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.0003
+'learning_rate': 0.01
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
@@ -51,7 +51,7 @@ model-index:
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 5e-05
+'ent_coef': 0.0009
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None

logs/events.out.tfevents.1691895801.4c5d58e91a6c.225.16

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a247b1c40602c6549efa00ad0c09df5457298f465d8e31d5efda583ac3d2a520
+size 143307

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abfc5d589874b79115d1d6c6f538db925b7f15ab241296e6a93e71d8c3bdfbd4
+oid sha256:5d538bc9a1eb6199bb73b7040be16f82d283cff319b1796d06045d8240a000ea
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -112.9129916957854, "std_reward": 61.0879027725272, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T03:02:37.852571"}
+{"env_id": "LunarLander-v2", "mean_reward": -95.71604316487536, "std_reward": 18.043357992945417, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T03:06:43.351432"}