Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -175.86 +/- 88.06
+      value: 168.08 +/- 135.53
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1
+'total_timesteps': 5000000
 'learning_rate': 0.0003
 'num_envs': 4
 'num_steps': 16

logs/events.out.tfevents.1683875702.PCPU21015.61568.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac1a6af93854ce75e63cb622715694470b0451f8328096d21e6581960c1687bb
+size 43155805

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b861ea139132cc4e9941b21f10cf537181074c4fa7170b8cdebc507bd316a9f2
+oid sha256:47368de404ba1d2fb47bb16bcc23d1a676419cd2fc57950356a2fe2d6b941fae
 size 42689

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -175.85986848879847, "std_reward": 88.06136341920248, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-12T15:10:31.600698"}
+{"env_id": "LunarLander-v2", "mean_reward": 168.0778956136193, "std_reward": 135.53367460159714, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-12T16:51:07.435179"}