Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 238.34 +/- 31.90
+      value: 230.60 +/- 98.07
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 1000000
-'learning_rate': 0.005
+'learning_rate': 0.001
 'num_envs': 4
 'num_steps': 1024
 'anneal_lr': True

logs/events.out.tfevents.1692001543.826fd7f89a0e.1472.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31b0bbbc058bbea92e20289200dd91b0affdaeaad65d7a8d9d0c59aebbe05e58
+size 567363

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0f968bda0fa94dbd9f34b17c1a4e07ca234458d53afdb20a7b01d1a1903eb08
+oid sha256:82924f15891ae85e2130f3f8c0b2078eea8fc2df73b817d50843f2bbc2cd4f0d
 size 8452763

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 238.33761440544907, "std_reward": 31.897387175202955, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-14T08:11:05.595354"}
+{"env_id": "LunarLander-v2", "mean_reward": 230.5994706969544, "std_reward": 98.06898999098453, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-14T08:45:53.194540"}