Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 118.98 +/- 45.61
+      value: 271.06 +/- 21.00
       name: mean_reward
       verified: false
 ---
@@ -38,13 +38,13 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 5000000
-'learning_rate': 0.0001
+'learning_rate': 0.001
 'num_envs': 32
 'num_steps': 512
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
-'gae_lambda': 0.98
+'gae_lambda': 0.97
 'num_minibatches': 128
 'update_epochs': 4
 'norm_adv': True

logs/events.out.tfevents.1681012072.bi-16.prod.env.980719.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a45f67a52b6598ac5cd5611278cc8db65530ba1ff51ad1eec0363bf41de35f90
+size 1529426

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:050cb35874011d852f260d55f39e6654eeba1db38c412b0d71684d286db14c99
+oid sha256:1ba159b847eb496d4033449077c3a4aedaa08e81ab58014d08266f3fb9d1dfa1
 size 42817

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 118.97601692003536, "std_reward": 45.60572219663702, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-09T03:43:11.730046"}
+{"env_id": "LunarLander-v2", "mean_reward": 271.059807158108, "std_reward": 21.000946616139945, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-09T04:50:39.503869"}