Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 60.26 +/- 69.09
+      value: -84.58 +/- 50.49
       name: mean_reward
       verified: false
 ---
@@ -40,11 +40,11 @@ model-index:
 'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 128
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
+'gamma': 0.999
+'gae_lambda': 0.98
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'utyug1/ppo-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 4096
+'minibatch_size': 1024}
     ```
     

logs/events.out.tfevents.1680990661.bi-16.prod.env.766592.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18c7d888e6cade2faf576bbfa8df6b2bde339fc6548f3e11105e286508c2a9c
+size 648565

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ba791dc7331097b7e18d251d984e1b5de9ba065fb3fa5b57349f0c975b98b8c
+oid sha256:a445c885d552a88115453fc2c7799ea5303c3b8e8a718cab64cbccee34f69fdc
 size 42817

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 60.26427900348342, "std_reward": 69.09237253712162, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-08T21:37:40.927702"}
+{"env_id": "LunarLander-v2", "mean_reward": -84.58338034513018, "std_reward": 50.487896941793046, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-08T21:54:26.929978"}