Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 151.12 +/- 130.54
+      value: 187.64 +/- 102.32
       name: mean_reward
       verified: false
 ---
@@ -52,7 +52,7 @@ model-index:
 'value_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
-'num_hiddens': 16
+'num_hiddens': 32
 'batch_size': 512
 'minibatch_size': 128}
   ```

logs/events.out.tfevents.1686530661.4c7cbfaa41ac.59942.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f2698bfd148daa768d02870639516ca4860f57a6786e539b154a1e0daf3f5f
+size 624258

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09ec321b3debc5bdafe15b8a4cb25af768c58463ef53dc4f0975fc61f73e96c3
-size 6949
+oid sha256:8d718df970e0cf713710e8bcb0807db358cba13e49c2c7c5c8ac47a08ffb4375
+size 14693

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 151.11725797317555, "std_reward": 130.54094318231103, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-12T00:43:22.915927"}
+{"env_id": "LunarLander-v2", "mean_reward": 187.64482632867697, "std_reward": 102.32410976208298, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-12T00:57:48.437303"}