Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -84.31 +/- 76.67
+      value: 8.23 +/- 104.95
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.005
+'learning_rate': 0.001
 'num_envs': 4
 'num_steps': 1024
 'anneal_lr': True

logs/events.out.tfevents.1691961342.bcadd1928d08.19432.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2310e507669fa730db51da25a1863a037f859ac1816f658c696c762b8a2b938
+size 70141

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8224c547b022af219efec1e7bc001b8d20fe3b1543436f4458b289b01f0533b6
+oid sha256:396ec0c6c24c34c3aed94f27f5556a495e77f8c5972c3859c414f450e62e67ff
 size 4285797

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -84.31454660447812, "std_reward": 76.66913382337074, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T21:10:46.362130"}
+{"env_id": "LunarLander-v2", "mean_reward": 8.233702475288291, "std_reward": 104.9518381870803, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T21:18:38.177446"}