Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 49.02 +/- 93.34
+      value: -238.15 +/- 136.41
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
-'learning_rate': 0.00025
+'total_timesteps': 50
+'learning_rate': 0.0025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
@@ -48,7 +48,7 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.05
+'clip_coef': 0.2
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1677885816.0726c440142d.7076.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e05727c3e7aba362d5d1b265a26d59bb70ee1f8878ee4822e9302c7289bcd4f
+size 677

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a98c47134add3fe86fe5e5c63babb6427287a7c8fab0e0b9b77f626e021fe264
+oid sha256:101150854b2b8737459c7dea8dede051ef3a05fb61b285d5cdbf6ef12c9b1ff5
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 49.01698398283622, "std_reward": 93.33703756122132, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-03T22:36:34.701177"}
+{"env_id": "LunarLander-v2", "mean_reward": -238.15198583331335, "std_reward": 136.40547173873318, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-03T23:23:47.262047"}