Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -158.33 +/- 110.09
+      value: -158.75 +/- 61.98
       name: mean_reward
       verified: false
 ---
@@ -39,12 +39,12 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
 'learning_rate': 0.00025
-'num_envs': 4
+'num_envs': 1024
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
+'gamma': 0.999
+'gae_lambda': 0.98
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'Ziyu23/lunar'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 131072
+'minibatch_size': 32768}
   ```
   

logs/events.out.tfevents.1685392133.63327b50afbb.46902.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c038b112ac6595b56d4ba634d4b4c87ee48bfdd9bfb9892947d3a60fed1eb75
+size 725

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a363dfe098933c96feb65ea5062a91e8aacf7448c05ac211c1404fb4e0f78d9
+oid sha256:e541b1708d23f31c9369b677df43ff11571f22fa1554ebef621b3cc7dae1051e
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -158.3304751513709, "std_reward": 110.08936950089767, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-29T20:15:56.511646"}
+{"env_id": "LunarLander-v2", "mean_reward": -158.74757441203224, "std_reward": 61.98199601684828, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-29T20:29:00.685744"}