Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -132.45 +/- 59.29
+      value: -212.20 +/- 116.89
       name: mean_reward
       verified: false
 ---
@@ -39,8 +39,8 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
 'learning_rate': 0.00025
-'num_envs': 16
-'num_steps': 1024
+'num_envs': 48
+'num_steps': 2048
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'bee-eater78/ppo-scratch-LunarLander-v1'
-'batch_size': 16384
-'minibatch_size': 4096}
+'batch_size': 98304
+'minibatch_size': 24576}
   ```
   

logs/events.out.tfevents.1720913847.5b2a566f3731.21874.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a74401da91bde5a6da45639fe9adc3f6f99e11d4763e4d0c85346eb774d2afd
+size 749

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25acf828f977452b0f56d3837acbdbe2d69cf0cba8b170bb3e66f1688da98401
+oid sha256:6924baa5dd037fce235630a196da2d3b4ab3db5b2a406adc766bdd0487a7d923
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -132.45420042026436, "std_reward": 59.2886900337752, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-13T23:36:01.540938"}
+{"env_id": "LunarLander-v2", "mean_reward": -212.20005389602716, "std_reward": 116.89020892819018, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-13T23:37:31.125285"}