Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -130.54 +/- 66.66
+      value: -13.46 +/- 92.01
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 300000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1677936177.51c135cbb35a.1943.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95d68f1a4cb6b6b3bde4c94d61d3be0da264ecf5786296d91d11742c0b8c4549
+size 466398

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
+oid sha256:19a401432defa3b8e71aa2e7ad670e2f0818638482c4baadcc8ce582197df316
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -130.5409671036616, "std_reward": 66.65580706532225, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-04T13:21:44.809245"}
+{"env_id": "LunarLander-v2", "mean_reward": -13.458361932575016, "std_reward": 92.0096374404238, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-04T13:29:40.825800"}