Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 8.74 +/- 65.86
+      value: -43.24 +/- 61.18
       name: mean_reward
       verified: false
 ---
@@ -44,14 +44,14 @@ model-index:
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
-'gae_lambda': 0.956973
+'gae_lambda': 0.98
 'num_minibatches': 128
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.384411
+'clip_coef': 0.2
 'clip_vloss': True
 'ent_coef': 0.01
-'vf_coef': 0.686165
+'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': 0.01
 'repo_id': 'zzen0008/ppo-LunarLander-v2'

logs/events.out.tfevents.1678612280.ZZDev.132345.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9493aa26027b5aa4025e48342efa911aed36375e68a78d741f8184fc43081324
+size 375240

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d568df4846288036e90892f8bfcf91271708d4d891dc28b5de33d3a3d1428280
+oid sha256:208e9826df7db92014b51ade27ec0ab7d5cfa2adb204a3f07a4ff9c8ce6c8c63
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 8.738130789360772, "std_reward": 65.86087328173129, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T20:07:29.566312"}
+{"env_id": "LunarLander-v2", "mean_reward": -43.23557848639608, "std_reward": 61.18001890154535, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T20:17:37.057520"}