Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -132.29 +/- 99.32
+      value: -168.58 +/- 76.20
       name: mean_reward
       verified: false
 ---
@@ -39,9 +39,9 @@ model-index:
 'f': '/root/.local/share/jupyter/runtime/kernel-034b7df4-145b-4db4-9d09-b6d875ced33d.json'
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.00022
+'learning_rate': 0.00024
 'num_envs': 4
-'num_steps': 192
+'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -56,7 +56,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'mgmeskill/ppo-LunarLander-v3'
-'batch_size': 768
-'minibatch_size': 192}
+'batch_size': 512
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1691895062.4c5d58e91a6c.225.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e3630b6486e1f2ccbb39ed70d7327261ef609fc78612c6190779d8b82b98f77
+size 207412

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fbad6a2fb836dbc3be939fac3f9e7ac223ee08e1191f2f0c71ae50b1e9a8c2f
+oid sha256:a717a7b46d613afca5e9a9eecab969dba1168a8005833a002725683fbc2137f3
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -132.29429884868858, "std_reward": 99.31866957760028, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:50:43.663470"}
+{"env_id": "LunarLander-v2", "mean_reward": -168.5756999427687, "std_reward": 76.20170511961085, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:52:39.589292"}