Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 5.02 +/- 56.86
+      value: -32.14 +/- 71.41
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
-'learning_rate': 0.0001
+'total_timesteps': 2000000
+'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1678323459.daniels-mbp.lan.73793.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50abfc83df826bea6c53f561c7c7ca68078f766c9b2cf921541d2cdc3cb46db1
+size 2534023

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:965b0d21a1748c01d5d16edd002ff313f7706d8a2b5a2c94af0894cd1ffc39ed
+oid sha256:373bc12c6163251916278d5778a5a0d6e2748cd405beaf6ef3b1333b1ae56206
 size 42689

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 5.019958474934308, "std_reward": 56.86162816665525, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-08T19:55:47.879660"}
+{"env_id": "LunarLander-v2", "mean_reward": -32.13920164324316, "std_reward": 71.4092374635304, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-08T20:42:47.771333"}