Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -162.52 +/- 97.64
+      value: -45.95 +/- 7.93
       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.1717178566.316a8236acd0.27263.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc22955e56940a2ecac4f4dfbdfa51e08d208564815db573f27d6b904b221303
+size 673751

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
+oid sha256:f77ef9c75a6010d53b638b2fbf6a0a2a078997ab1d6d29a1b7ff740ac1d0c4bf
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -162.52240830577233, "std_reward": 97.64322471534834, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-31T17:50:36.587533"}
+{"env_id": "LunarLander-v2", "mean_reward": -45.95253548075217, "std_reward": 7.932959199582704, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-31T18:17:29.634285"}