Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -145.08 +/- 96.15
+      value: -150.98 +/- 104.29
       name: mean_reward
       verified: false
 ---
@@ -39,13 +39,13 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
 'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 128
+'num_envs': 8
+'num_steps': 256
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 4
+'num_minibatches': 8
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'Junfeng/LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 2048
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1677999752.fc3f81300349.12437.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2691dc233daf7b211bc7aec80e7010a116de4f98817bbdb5c70c88ea8400147
+size 74636

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
+oid sha256:fb7f5eb6236ee396c6e5d3cd64d551c75ef150de2f6d401b7081be1ecc49f30b
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -145.08436574038248, "std_reward": 96.1492858886998, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-05T06:54:04.447122"}
+{"env_id": "LunarLander-v2", "mean_reward": -150.9765478094132, "std_reward": 104.28775996788302, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-05T07:03:02.805267"}