Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -193.84 +/- 121.68
+      value: -128.00 +/- 82.88
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1680323116.d090693a7f22.3351.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9614cbc514adc60a4fb925d2c0b3cd456f7ebddab9898d313f5dbc5da0176c0d
+size 211280

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b960e870eeebf645686f7193c61bc4ddbdd89a326936f5ee006c093519943ec1
+oid sha256:d5a799e909e73bccaa9629be9698ce5d31184df8212e993d7ab7d3223c4cfffb
 size 42817

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -193.83839456170935, "std_reward": 121.67695347301456, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-01T04:23:54.579992"}
+{"env_id": "LunarLander-v2", "mean_reward": -127.99899146223632, "std_reward": 82.88069821274007, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-01T04:26:02.246193"}