Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -101.37 +/- 105.81
+      value: -156.84 +/- 68.01
       name: mean_reward
       verified: false
 ---
@@ -37,14 +37,14 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 200000
-'learning_rate': 0.0001
+'total_timesteps': 500000
+'learning_rate': 1e-05
 'num_envs': 8
 'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.95
-'gae_lambda': 0.9
+'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 5
 'norm_adv': True

logs/events.out.tfevents.1698070897.527fe3665085.17894.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:418f9deb479f6bf1a986a94372f597605d217016b277c5fbd12aa5c52b071f50
+size 872088

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aa3f2ccccbe18d1c4a1776928d6dd0aa4a001f10967f17ade8d1ccc6cf590ea
+oid sha256:1cb9866b1ef0934d0a4d11aac5359c79822a9e609c18874326fbc774a9fbcc2e
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -101.36909513759574, "std_reward": 105.81349426233422, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T14:18:21.958204"}
+{"env_id": "LunarLander-v2", "mean_reward": -156.84411362634867, "std_reward": 68.01235352547111, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T14:26:10.119748"}