Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 75.67 +/- 130.43
+      value: 97.20 +/- 138.21
       name: mean_reward
       verified: false
 ---
@@ -36,17 +36,17 @@ model-index:
 'wandb_project_name': 'cleanRL'
 'wandb_entity': None
 'capture_video': False
-'f': '/root/.local/share/jupyter/runtime/kernel-034b7df4-145b-4db4-9d09-b6d875ced33d.json'
+'f': '/root/.local/share/jupyter/runtime/kernel-b1e556d7-bdda-4e73-8875-1705f0553981.json'
 'env_id': 'LunarLander-v2'
 'total_timesteps': 1000000
-'learning_rate': 0.001
+'learning_rate': 0.002
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.88
-'num_minibatches': 4
+'num_minibatches': 8
 'update_epochs': 3
 'norm_adv': True
 'clip_coef': 0.2
@@ -57,6 +57,6 @@ model-index:
 'target_kl': None
 'repo_id': 'mgmeskill/ppo-LunarLander-v3'
 'batch_size': 512
-'minibatch_size': 128}
+'minibatch_size': 64}
   ```
   

logs/events.out.tfevents.1691973444.0e3254ff3216.1772.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e437a82322960219595be6741be1d1f048532dabc8a0f6c567b8631ccfefb6a4
+size 1339420

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7318ca5d8ba02dd302edbdd734254608492fb3f0e1e02927343fd2c9a0a1dca9
+oid sha256:c5dc13827e3f4f3827407c495260cac7c0f5ca6e5c147ebfdfc89acc69bd9816
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 75.66851044080843, "std_reward": 130.43451595374478, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T03:42:52.455396"}
+{"env_id": "LunarLander-v2", "mean_reward": 97.20057038570272, "std_reward": 138.21382178930205, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-14T01:01:03.576708"}