Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -155.49 +/- 122.14
+      value: -138.98 +/- 47.47
       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': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1712114872.dlserver.210835.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:385ba28d2baa79d27048a6c50e6b2c3f93c89507955847061a2c2c4a17ade40c
+size 221325

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad3e3e7c4e96740c86f9ad51d24665843cea40cdd87752721230de4d9014ee19
+oid sha256:952ddc07afdb42e66b5257f406f3306d68e8b1204ea1a30069aafe1352f759b9
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -155.4929042795509, "std_reward": 122.13975723302488, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-03T11:26:55.495188"}
+{"env_id": "LunarLander-v2", "mean_reward": -138.9823469050284, "std_reward": 47.46734538802742, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-03T11:28:49.209196"}