Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 330.10 +/- 123.28
+      value: 64.60 +/- 27.55
       name: mean_reward
       verified: false
 ---
@@ -40,11 +40,11 @@ model-index:
 'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 128
+'num_steps': 1028
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
+'gamma': 0.999
+'gae_lambda': 0.99
 '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': 'FabioDataGeek/LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 4112
+'minibatch_size': 1028}
   ```
   

logs/events.out.tfevents.1683008945.fabio-Katana-GF66-12UC.9837.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5cbd904d991543c6643e3d8595a895effcdd354d77df1ee90ae28eb540b60b9
+size 334221

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:363abdb4c5fb84fe61c60e399ab7f117ac69159d94a377b35c06cbdcb445a112
+oid sha256:8abf9208b60a055fa6087b91d44acf023e07d7ecc71a85604c96e0a6c556fe60
 size 39909

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 330.1, "std_reward": 123.28458946681049, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-02T08:21:35.721550"}
+{"env_id": "CartPole-v1", "mean_reward": 64.6, "std_reward": 27.547050658827345, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-02T08:32:05.578145"}