Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -121.68 +/- 110.10
+      value: -7.07 +/- 99.54
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 30000
+'total_timesteps': 50000
 'learning_rate': 0.002
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1733515882.09eb592846a0.10026.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb35faf0b5f3c77d30ab4f9d8aafe3854e436a74a93b20520079b2e46ca240ea
+size 83846

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32d7e86a2950ba03671e86cd957904575dd6dd7af95e14290ff3d03045ec8043
+oid sha256:43911bf283c2515872b4cbce899e15102bd7de7b192d9e2beb962d05d2c924fe
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -121.6801996642218, "std_reward": 110.10188488950595, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-06T20:10:47.905624"}
+{"env_id": "LunarLander-v2", "mean_reward": -7.066432356477476, "std_reward": 99.53911593703612, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-06T20:12:32.768628"}