Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -50.09 +/- 113.07
+      value: -27.96 +/- 50.99
       name: mean_reward
       verified: false
 ---
@@ -44,14 +44,14 @@ model-index:
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
-'gae_lambda': 0.896973
+'gae_lambda': 0.956973
 'num_minibatches': 128
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.384411
 'clip_vloss': True
 'ent_coef': 0.01
-'vf_coef': 0.786165
+'vf_coef': 0.686165
 'max_grad_norm': 0.5
 'target_kl': 0.01
 'repo_id': 'zzen0008/ppo-LunarLander-v2'

logs/events.out.tfevents.1678611188.ZZDev.127898.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2acf52353e74c86704b670efacfa6206ecf8d63c4cbda5f5bfe6449c4b93d191
+size 336556

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:062579449773d86c85391bdd1b3e2095fec26c301b7cbe4b0b6ef262b8732d40
+oid sha256:d568df4846288036e90892f8bfcf91271708d4d891dc28b5de33d3a3d1428280
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -50.08888548974316, "std_reward": 113.07297848822984, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T19:51:48.160348"}
+{"env_id": "LunarLander-v2", "mean_reward": -27.95528455619949, "std_reward": 50.98508167661688, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T19:59:38.157468"}