Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -133.01 +/- 59.83
+      value: -19.44 +/- 112.71
       name: mean_reward
       verified: false
 ---
@@ -45,15 +45,15 @@ model-index:
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
-'gae_lambda': 0.97
+'gae_lambda': 0.92
 'num_minibatches': 4
-'update_epochs': 1
+'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.015
-'vf_coef': 0.25
-'max_grad_norm': 0.25
+'ent_coef': 0.005
+'vf_coef': 0.5
+'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'mgmeskill/ppo-LunarLander-v3'
 'batch_size': 512

logs/events.out.tfevents.1691894298.4c5d58e91a6c.225.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:957cf8d4f685b449db5df75ef213d6b89dc662249d64d5cf6bdd93944ee4ff85
+size 156493

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:760136cdba079d759c4e24069c2b470074bb9f8d9a00a677ecd8ad53bd9af41e
+oid sha256:b7014ce45d24c2ceac222d20171ab69e6c5b0317b08e32ac9a22a0d5e10505ef
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -133.01069418612266, "std_reward": 59.82798516461417, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:38:06.442848"}
+{"env_id": "LunarLander-v2", "mean_reward": -19.440788101191153, "std_reward": 112.71072222129561, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:40:32.416642"}