Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -121.12 +/- 113.00
+      value: -170.02 +/- 76.39
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
+'total_timesteps': 25000
 'learning_rate': 2e-05
 'num_envs': 3
 'num_steps': 64

logs/events.out.tfevents.1690582165.3264a592252d.2200.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f8f503bb5eba9e4042fa339fc7dad2318b94255b1f9e3dab67f05a6709511ee
+size 98589

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75897c256f4568c4886dce0da55113490b358725501de972980a46ecb2ef9ffb
+oid sha256:3750449b5f66a973f1bb9eb95e8a7a44a230184fe66d75d4d99fee5dee7916f3
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -121.12026975147424, "std_reward": 113.00067765858311, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-28T17:53:24.325654"}
+{"env_id": "LunarLander-v2", "mean_reward": -170.02054304900693, "std_reward": 76.39435714913401, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-28T22:09:48.932088"}