Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -204.77 +/- 118.97
+      value: -44.41 +/- 19.85
       name: mean_reward
       verified: false
 ---
@@ -37,14 +37,14 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 2000000
-'learning_rate': 1e-07
+'total_timesteps': 3000000
+'learning_rate': 2.5e-05
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
-'gae_lambda': 0.98
+'gamma': 0.999
+'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True

logs/events.out.tfevents.1677680543.218c4c1a453f.17491.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de6d3d6db1d65aba4bfb0370f7380be052657b6de0c7107a1f35547315feef23
+size 4119164

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4966060a548122040599af91e5134e129b766c6951117fe5ff4e13976988247
+oid sha256:a822d5a20a0f49d3b2b0875e7c1e6d97cd7360777c198adb435c291e97216808
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -204.77273059578064, "std_reward": 118.97132587123544, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-01T14:20:53.439384"}
+{"env_id": "LunarLander-v2", "mean_reward": -44.41426102848249, "std_reward": 19.848558505941174, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-01T15:40:14.503436"}