Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -179.05 +/- 120.28
+      value: -163.40 +/- 72.18
       name: mean_reward
       verified: false
 ---
@@ -39,23 +39,23 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
 'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 128
+'num_envs': 16
+'num_steps': 512
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
+'gamma': 0.999
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.01
+'ent_coef': 0.02
 'vf_coef': 0.5
-'max_grad_norm': 0.5
+'max_grad_norm': 0.3
 'target_kl': 0.015
 'repo_id': 'miki030/lunar2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 8192
+'minibatch_size': 2048}
   ```
   

logs/events.out.tfevents.1693209478.d39058c94989.8807.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90d91fa5dd85cd78919e54f872406d8167046b47e13cd4c7b0d1f44ffc477854
+size 61040

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba9eba95178b8c1eeff91f1866f65cb2c8b1c65ceedc704e4da139555fb0614
+oid sha256:bb630396dcb2290e0f0ae6c950529d1eea10233490d308c1b1c069f43bd049a6
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -179.0538394106519, "std_reward": 120.28112490634173, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-28T07:55:13.426272"}
+{"env_id": "LunarLander-v2", "mean_reward": -163.40478929612743, "std_reward": 72.17678192937309, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-28T07:58:19.343356"}