Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -136.69 +/- 74.75
+      value: 120.19 +/- 117.97
       name: mean_reward
       verified: false
 ---
@@ -37,15 +37,15 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
-'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 128
+'total_timesteps': 250000
+'learning_rate': 0.003
+'num_envs': 8
+'num_steps': 256
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 4
+'num_minibatches': 8
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'Epoching/ppo-scratch-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 2048
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1714383499.bigteddy.1453.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75e40f663aa35f6314aad6701f28539e155be1318f04cc9e8116020aa2ac942e
+size 153371

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecfbbf5b5f02683ca1ed29a3d4ca211218c1938a860da7d67aefb3f13056d5f2
+oid sha256:4d8e5a5fb305a311be429e7ef7b6e86adfe53e2be4490e08db984a0752a7c048
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -136.69187828324698, "std_reward": 74.7525513960982, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-29T02:31:05.200230"}
+{"env_id": "LunarLander-v2", "mean_reward": 120.18795126033994, "std_reward": 117.97431146207656, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-29T02:44:26.268683"}