Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -41.69 +/- 53.75
+      value: 24.37 +/- 97.04
       name: mean_reward
       verified: false
 ---
@@ -37,10 +37,10 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 550000
-'learning_rate': 0.0003
+'total_timesteps': 650000
+'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 256
+'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -48,14 +48,14 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.2
+'clip_coef': 0.25
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'kinkpunk/PPO-LunarLander'
-'batch_size': 1024
-'minibatch_size': 256}
+'batch_size': 512
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1676839049.e00ba7557307.36933.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce4b1b42e42be8e4039cf380669248423a206a66186bbda72ca4580dc7a3c537
+size 863671

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:172fe45cbf8992f0cb1f5d6ced0dcefcf4bd151c22304f4c22cf086d231537be
+oid sha256:19a9f041cebe7c590c11c5d4790cb0634d47593b62a7bab8e14a15228ca97f2b
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -41.692552472580324, "std_reward": 53.74714583676262, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T20:29:28.060964"}
+{"env_id": "LunarLander-v2", "mean_reward": 24.374281226444914, "std_reward": 97.03775218215073, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T20:55:36.577077"}