Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -130.67 +/- 54.85
+      value: -152.74 +/- 99.16
       name: mean_reward
       verified: false
 ---
@@ -38,15 +38,15 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.00025
-'num_envs': 4
+'learning_rate': 0.001
+'num_envs': 5
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
+'gamma': 0.75
+'gae_lambda': 0.99
 'num_minibatches': 4
-'update_epochs': 4
+'update_epochs': 5
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'niltheory/ppo-LunarLanderv2u8'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 640
+'minibatch_size': 160}
   ```
   

logs/events.out.tfevents.1701201538.e705ad2e6486.19920.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:189967afd29d50b0db903df3c2e165ef9690b7cd7b8c82f5d8b7c837eb1802be
+size 69200

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b51141f29a5fd60d9f7a96a70a1e185897fcb1c4838b12131a7276001db13c08
+oid sha256:1e83cc8b8fa3f3d97050ea7f23630f49c6481abc1f511ddaa99be59bcd749ac5
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -130.6748095205718, "std_reward": 54.84788216866614, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-28T19:54:41.705277"}
+{"env_id": "LunarLander-v2", "mean_reward": -152.73803951927806, "std_reward": 99.16277580962758, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-28T20:00:03.211512"}