Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -111.15 +/- 50.39
+      value: -51.51 +/- 93.21
       name: mean_reward
       verified: false
 ---
@@ -37,16 +37,16 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
-'learning_rate': 0.00025
-'num_envs': 4
+'total_timesteps': 1000000
+'learning_rate': 0.0003
+'num_envs': 1024
 'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 4
-'update_epochs': 4
+'num_minibatches': 1024
+'update_epochs': 6
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'jjhonny/LundarLander-v2-custom'
-'batch_size': 512
+'batch_size': 131072
 'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1688532790.b5cab0aab5c1.51708.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:185d109e6f4e1b9930a13b66b4fed110820db0bf5e2eaa7f55db671e302770d6
+size 105533

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5474aae4cc0d8669583d102be61d425b33b06b7b07d34411b9508052b6239d8
-size 42469
+oid sha256:d8dcb4194d0f0fad6670694683480f7843e06d91451e12faf5785a20228da389
+size 553189

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -111.15393189772658, "std_reward": 50.38975110405267, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-05T04:47:49.181406"}
+{"env_id": "LunarLander-v2", "mean_reward": -51.50794115983897, "std_reward": 93.20573428963354, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-05T04:56:43.118514"}