Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -190.81 +/- 114.26
+      value: -186.56 +/- 75.63
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 5000
+'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 64

logs/events.out.tfevents.1744817970.Cyprien-Bone-UCL.455303.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adca42609c636ef6b587c0e46a89e60989af4956024ffc8d272ad8c253d1222a
+size 161026

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0258cf1221db5d39461b5c9bf569456775a8233ec7ba59f71d4590da0e7bb1a
+oid sha256:ed2a57baa2f6d0e26c893a4340b0d46c12e4c07b702b37361b9d15e152f9ff5d
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -190.8093250777072, "std_reward": 114.25500374699762, "n_evaluation_episodes": 10, "eval_datetime": "2025-04-16T16:38:49.791187"}
+{"env_id": "LunarLander-v2", "mean_reward": -186.5592731018887, "std_reward": 75.6305520607916, "n_evaluation_episodes": 10, "eval_datetime": "2025-04-16T16:41:30.680773"}