Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -197.03 +/- 101.79
+      value: -121.68 +/- 110.10
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 30000
-'learning_rate': 0.00025
+'learning_rate': 0.002
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1733515815.09eb592846a0.9729.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f918b057ccf89a38c8ed3337e2717da15670bb6d2a3325027c15b2f77847026
+size 57715

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1670328fe656e103e38b60de64dad3cb675346abe328d2d3b02b5b47fb159cb
+oid sha256:32d7e86a2950ba03671e86cd957904575dd6dd7af95e14290ff3d03045ec8043
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -197.03045107703926, "std_reward": 101.79290400214262, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-06T20:09:21.711206"}
+{"env_id": "LunarLander-v2", "mean_reward": -121.6801996642218, "std_reward": 110.10188488950595, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-06T20:10:47.905624"}