Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -91.52 +/- 44.69
+      value: -120.16 +/- 68.96
       name: mean_reward
       verified: false
 ---
@@ -38,15 +38,15 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 200000
-'learning_rate': 0.00025
+'learning_rate': 0.0001
 'num_envs': 8
 'num_steps': 256
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
-'gae_lambda': 0.98
+'gae_lambda': 0.9
 'num_minibatches': 4
-'update_epochs': 4
+'update_epochs': 5
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True

logs/events.out.tfevents.1698069434.527fe3665085.11743.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bc4aeab8efac8f9a703dc0b0850e2ec7e22eb84e434877b3a06038afc6cd263
+size 277110

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bbcc544786aab47d233499b1f0cba9d6c0fe809d08b1a73c1ef085c4cec99af
+oid sha256:f17c37302f89fceb3a52293d667da8b9a1f35b2db32425783f6da817ed8e3d81
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -91.51678888577757, "std_reward": 44.69222938531735, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T13:46:15.044441"}
+{"env_id": "LunarLander-v2", "mean_reward": -120.1608083562626, "std_reward": 68.9613468550431, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T13:58:58.195547"}