Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 46.04 +/- 80.34
+      value: -99.99 +/- 51.57
       name: mean_reward
       verified: false
 ---
@@ -44,16 +44,16 @@ model-index:
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.9
-'gae_lambda': 0.95
+'gamma': 0.99
+'gae_lambda': 0.97
 'num_minibatches': 4
-'update_epochs': 2
+'update_epochs': 1
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.01
-'vf_coef': 0.5
-'max_grad_norm': 0.5
+'ent_coef': 0.015
+'vf_coef': 0.75
+'max_grad_norm': 0.75
 'target_kl': None
 'repo_id': 'mgmeskill/ppo-LunarLander-v3'
 'batch_size': 512

logs/events.out.tfevents.1691894099.4c5d58e91a6c.225.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b1d31335f68314e232b0826e5835e2a276031f8357c32e2c9757137839da19d
+size 217095

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31476b528f28f631470f505ff9a0372f472596d7801d58a621140ab7db3a0804
+oid sha256:3f13198e1466ec011aeede1eca79b4f85e6f120b033e44a7b46a1a23c13bbf27
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 46.042900408334816, "std_reward": 80.33997287187769, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:34:42.788862"}
+{"env_id": "LunarLander-v2", "mean_reward": -99.99204338679954, "std_reward": 51.568848623875674, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:36:19.263890"}