Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -37.21 +/- 26.03
+      value: -161.38 +/- 116.98
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.001
+'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1677149719.17a49215cfb3.39885.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1e9112d7b837954a1749056b209f83749f2242978dafa5d23c62c0f157e92c0
+size 216801

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fc5a595b9088065da31a3c860d28a07922e4f3c6b9f458518da1886ea0249ac
+oid sha256:bcd2d09ce108a051e2e384d5e01bda71dd42ff9b117e243d3d4f61911fd43a9d
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -37.20970721180714, "std_reward": 26.027109408286094, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-23T10:53:32.256702"}
+{"env_id": "LunarLander-v2", "mean_reward": -161.37644260208086, "std_reward": 116.97669573720529, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-23T10:56:41.607918"}