Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -38.53 +/- 88.82
+      value: -88.30 +/- 87.78
       name: mean_reward
       verified: false
 ---
@@ -37,13 +37,13 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
+'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
+'gamma': 0.95
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4

logs/events.out.tfevents.1703596318.cybertron.1474.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c03ae65e8d9c1dfa1894ccb6392004334069f6d8ae03c9e204d0912f89cdb10
+size 90393

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ec1bb294ab91145c06f690741e789ab992b53a8bb13a508045025421968427
+oid sha256:b4a03fa728a33b1506a43ac3083bbddd5cb59ee0f8d480281fbb3d8c2db6cc20
 size 672534

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -38.52591058773196, "std_reward": 88.81729419429954, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-26T21:00:28.970749"}
+{"env_id": "LunarLander-v2", "mean_reward": -88.30457757926787, "std_reward": 87.78342986788695, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-26T21:12:39.297008"}