Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -120.78 +/- 61.90
+      value: 29.71 +/- 115.22
       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': 2000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1677697464.3fc115447c45.9780.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e6b168ef9ef826002c042794399134f53e4410488811f3ea17276cc94a18df1
+size 2732220

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
+oid sha256:1cef3a0448d7e91183f0d46c06531b06b27d9abc0760e9eb8a10d12f654b7268
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -120.78004317056741, "std_reward": 61.89799184891244, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-01T19:03:52.890912"}
+{"env_id": "LunarLander-v2", "mean_reward": 29.70662471264138, "std_reward": 115.22024266282554, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-01T19:46:08.929141"}