Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -5.52 +/- 86.96
+      value: 72.56 +/- 59.08
       name: mean_reward
       verified: false
 ---
@@ -39,14 +39,14 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 500000
 'learning_rate': 0.0003
-'num_envs': 4
-'num_steps': 128
+'num_envs': 8
+'num_steps': 512
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.98
-'num_minibatches': 4
-'update_epochs': 4
+'num_minibatches': 8
+'update_epochs': 8
 'norm_adv': True
 'clip_coef': 0.1
 'clip_vloss': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'yumingyi/lunarlander-v2-unit8'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 4096
+'minibatch_size': 512}
   ```
   

logs/events.out.tfevents.1680168411.9015aca90cf1.36108.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2e9d5adeab6d860cb2280d8543e26612e8bd4428c56f9b6abab1d22d21fc3d2
+size 63489

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec11a0bf4cd41f4d7502e7fce3d51436a8b46926980f7bb7706a6b03b85d95b5
+oid sha256:37fd6388fa8e524b7672f4f59d3fe6e48405e01046e9d8a680fd007a11fe952d
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -5.524101016230057, "std_reward": 86.95777608679323, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-30T09:24:41.545469"}
+{"env_id": "LunarLander-v2", "mean_reward": 72.5568676266118, "std_reward": 59.08436386889436, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-30T09:37:22.337265"}