Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 61.08 +/- 111.86
+      value: -207.17 +/- 124.73
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
+'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1690153222.0c05bac17d51.12242.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86516688ac1da23b97167f5462b5f1fcff3abc0b85096df87a09dcc6c19607e1
+size 101076

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d7ca9d094a695f309c8f59fe5c7ada825cb4baebdecf651ad75721ad0e1b6e8
+oid sha256:ac8780d18a4642139a7866008ca59e476adc2aadbe0ecbdd073916ef5789b06d
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 61.08392345745155, "std_reward": 111.85838102133705, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-23T22:52:21.927052"}
+{"env_id": "LunarLander-v2", "mean_reward": -207.17163166065228, "std_reward": 124.73085921995373, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-23T23:01:12.232166"}