Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -170.17 +/- 84.74
+      value: 112.64 +/- 121.59
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 75000
+'total_timesteps': 7500000
 'learning_rate': 0.00015
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1682682503.507b886ba908.4094.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90c7913e0dd21d99a00e4bc8483fe0700f0ebb97ad88a0882583a44fb8e3aca2
+size 11056355

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2daf4a198e6f36f16dc5c3f574695be30b96984cf7d2310b583119cc0980a0f3
+oid sha256:59d68bde6aa0ce849fdb5d931bf069513bc94c545e2b72dd8d578991a08e0794
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -170.16765100714554, "std_reward": 84.73838833410407, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-28T11:47:48.956843"}
+{"env_id": "LunarLander-v2", "mean_reward": 112.6413019706085, "std_reward": 121.58910516764863, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-28T14:10:28.345279"}