Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -164.11 +/- 61.52
+      value: 76.01 +/- 68.86
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1677485839.af82a49f2879.14961.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:198a58fd4aeea86da15e01918e619fa604101de17b0754b3a1acc763f6bc6753
+size 659808

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
+oid sha256:a9f46f0c7b70f362e72eed22c3293e3d84fecfb7f3a67337d95096ecff1763a0
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -164.1097335794363, "std_reward": 61.5165029108348, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-27T08:15:45.384569"}
+{"env_id": "LunarLander-v2", "mean_reward": 76.01097346993338, "std_reward": 68.85969890523657, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-27T08:31:44.378222"}