Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -131.38 +/- 83.11
+      value: -46.67 +/- 22.05
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1707932287.bd3cf3813bfe.3881.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad757d3016ba2720fbd540d7da7c6fe2e42ce9758c80f4a217f4fec97afe35d9
+size 673768

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf4a7fde3320b1226867f811244d8c33574eca701ec88ceee90bda5c8724f5d8
+oid sha256:f77ef9c75a6010d53b638b2fbf6a0a2a078997ab1d6d29a1b7ff740ac1d0c4bf
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -131.37562498289952, "std_reward": 83.11457211991204, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-14T17:37:30.911890"}
+{"env_id": "LunarLander-v2", "mean_reward": -46.6722082852104, "std_reward": 22.04603589771762, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-14T17:52:09.801386"}