Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 131.11 +/- 19.44
+      value: 114.29 +/- 33.98
       name: mean_reward
       verified: false
 ---
@@ -42,8 +42,8 @@ model-index:
 'anneal_lr': True
 'gae_lambda': 0.98
 'gamma': 0.999
-'minibatch_size': 64
-'update_epochs': 4
+'minibatch_size': 256
+'num_epochs': 16
 'adv_norm': True
 'clip_coef': 0.2
 'clip_value_loss': True
@@ -51,7 +51,7 @@ model-index:
 'value_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
-'num_hiddens': 64
+'num_hiddens': 32
 'batch_size': 16384}
   ```
   

logs/events.out.tfevents.1686564019.b5583796e1dd.10687.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c4fdb47f10de4ca58dcd716bffcf8c09b6b2b607bd242dd78163d39a83e7ebe
+size 298922

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37ecd59eab111db156124b74534dc890c3d3d81a630b4e14ad5d1149e75595d2
-size 42469
+oid sha256:463283a69c0731927b84f17f8bf2b2492da3fa497117055e372c8d3d9205e75e
+size 14693

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 131.11012219770583, "std_reward": 19.43670847824517, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-12T09:51:56.059748"}
+{"env_id": "LunarLander-v2", "mean_reward": 114.29204195524281, "std_reward": 33.98275875153536, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-12T10:31:49.127066"}