Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -190.38 +/- 130.94
+      value: -119.69 +/- 40.93
       name: mean_reward
       verified: false
 ---
@@ -38,10 +38,10 @@ model-index:
 'capture_video': False
 'f': '/root/.local/share/jupyter/runtime/kernel-13ae2347-2156-49eb-80c5-a8b483ae1b52.json'
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
-'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 128
+'total_timesteps': 250000
+'learning_rate': 0.00022
+'num_envs': 16
+'num_steps': 256
 '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': 512
-'minibatch_size': 128}
+'batch_size': 4096
+'minibatch_size': 1024}
   ```
   

logs/events.out.tfevents.1691881668.f7c6ccb2950d.678.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4714759e8a636a81a935591b63a1fd0a40e440ef226f60575cd0472daa165264
+size 322697

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c706c81696f37ceaeb74d41e1262ec54c4e2f63b8cbb791c8b01decf796f6a53
+oid sha256:499a30ac8ed4e62158bcc9bfb08527fc70c2a83a2fcb112252276447e25567ae
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -190.38133106509355, "std_reward": 130.93739060228106, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-12T23:06:56.825322"}
+{"env_id": "LunarLander-v2", "mean_reward": -119.68585316751664, "std_reward": 40.93082158469233, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-12T23:09:22.933489"}