Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 9.40 +/- 51.21
+      value: -106.83 +/- 87.57
       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': 0.001
+'learning_rate': 0.0001
 'num_envs': 4
-'num_steps': 128
+'num_steps': 192
 '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': 768
+'minibatch_size': 192}
   ```
   

logs/events.out.tfevents.1691894748.4c5d58e91a6c.225.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aed24e6864fd743ed0b490cae63cc21e1a081e2c0013138c0d9918d14dbc7a3
+size 186686

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ef1068c332f17e5bdc476fdfcbe39f4818441458145faffb65e9e609660a121
+oid sha256:9350b1b7c6d4e43f5d5202fc8456eb98d4577f04aa0e9a839e1e704aa7175bbf
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 9.400729433379885, "std_reward": 51.212038162468836, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:44:17.144996"}
+{"env_id": "LunarLander-v2", "mean_reward": -106.8300660569799, "std_reward": 87.57369656844713, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:47:14.949731"}