Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -129.00 +/- 80.90
+      value: 1.24 +/- 95.74
       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': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1679177747.anderson.406889.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659892691e568283a64f33ff56976a1ce32d0143f223cd876b5b978e3f07e53d
+size 670529

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:478d3e8467367544c2997b369b551e8a0773f795cd9e2b9a9ccea4baf859b74a
+oid sha256:fd516d63d3690fa277dea5f8bb1d7386bbb6aad6c274a76293c7902cc4c1c72f
 size 42817

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -128.99674940829954, "std_reward": 80.89780515117073, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-18T22:15:28.527225"}
+{"env_id": "LunarLander-v2", "mean_reward": 1.2376865302526157, "std_reward": 95.73553237514322, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-18T22:27:00.389626"}