Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -164.93 +/- 88.09
+      value: -44.52 +/- 85.75
       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_envs': 6
 'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
-'gae_lambda': 0.95
-'num_minibatches': 4
-'update_epochs': 4
+'gae_lambda': 0.97
+'num_minibatches': 10
+'update_epochs': 10
 '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': 'HusseinEid/ppo-LunarLander-v2-from-scratch'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 768
+'minibatch_size': 76}
   ```
   

logs/events.out.tfevents.1714309692.4f7e93093a7f.2881.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f516e6ba0f8eb3d75716b7331f59e06fa6d56c0375c881b6033eaa24589ad333
+size 70278

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b51141f29a5fd60d9f7a96a70a1e185897fcb1c4838b12131a7276001db13c08
+oid sha256:5687ee1d5c8d4748077b77ff955ceb0049782356e3dfe1f7727361f26661d7c1
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -164.92893386969695, "std_reward": 88.09017859194573, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-28T13:04:38.113378"}
+{"env_id": "LunarLander-v2", "mean_reward": -44.515785329977845, "std_reward": 85.7539446390707, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-28T13:09:26.068668"}