Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -120.16 +/- 68.96
+      value: -101.37 +/- 105.81
       name: mean_reward
       verified: false
 ---
@@ -40,10 +40,10 @@ model-index:
 'total_timesteps': 200000
 'learning_rate': 0.0001
 'num_envs': 8
-'num_steps': 256
+'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.999
+'gamma': 0.95
 'gae_lambda': 0.9
 'num_minibatches': 4
 'update_epochs': 5
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'jfelgate/ppo-LunarLander-v2'
-'batch_size': 2048
-'minibatch_size': 512}
+'batch_size': 1024
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1698070565.527fe3665085.16459.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35bf0d1a941b7e1cc3f7a1e802d478e041027e4d654c3173a7c8cfbaaed7924e
+size 275765

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f17c37302f89fceb3a52293d667da8b9a1f35b2db32425783f6da817ed8e3d81
+oid sha256:2aa3f2ccccbe18d1c4a1776928d6dd0aa4a001f10967f17ade8d1ccc6cf590ea
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -120.1608083562626, "std_reward": 68.9613468550431, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T13:58:58.195547"}
+{"env_id": "LunarLander-v2", "mean_reward": -101.36909513759574, "std_reward": 105.81349426233422, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T14:18:21.958204"}