Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -125.30 +/- 66.37
+      value: -24.70 +/- 52.00
       name: mean_reward
       verified: false
 ---
@@ -37,14 +37,14 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 500000
 'learning_rate': 0.00025
-'num_envs': 4
+'num_envs': 16
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
+'gamma': 0.9995
+'gae_lambda': 0.97
 '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': 'grib0ed0v/ppo-LunarLander-v2-unit8'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 2048
+'minibatch_size': 512}
   ```
   

logs/events.out.tfevents.1728031923.32e588a9c7ee.15342.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2259023b29d2a5de328b242090cfc22fde7a35155deffb054accb3f6408a7040
+size 552588

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
+oid sha256:ce9fe69889acbcf8344df8324cf4aa1545cd56fc8766b3883529cb2f2613e955
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -125.30431640320857, "std_reward": 66.37274771061621, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-04T08:21:33.863344"}
+{"env_id": "LunarLander-v2", "mean_reward": -24.6983643934922, "std_reward": 52.00093006149238, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-04T08:56:25.536757"}