Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -12.67 +/- 67.29
+      value: -66.84 +/- 63.69
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 500000
-'learning_rate': 0.00025
+'learning_rate': 0.0001
 'num_envs': 16
 'num_steps': 128
 'anneal_lr': True
@@ -48,7 +48,7 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 '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.1676591825.16efff3e153a.13698.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a72a57213cf7e7e13e16e28f6f3c4a6e64a66112ec3abcaf6c1a54a54b07428f
+size 520920

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:130267ed6be293e08f2610e4a2dedb99da2f4b413a3a0e448dc713772dc4f13c
+oid sha256:09959bf881bcb01e400be20167885f7b0f154b80be72cf081ca34722c4317a00
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -12.669906858983111, "std_reward": 67.29191703523182, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-16T23:52:38.481886"}
+{"env_id": "LunarLander-v2", "mean_reward": -66.8426411104437, "std_reward": 63.691851247331954, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T00:01:42.190356"}