Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -140.85 +/- 109.45
+      value: -25.85 +/- 39.85
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
-'learning_rate': 0.00025
+'total_timesteps': 500000
+'learning_rate': 0.0001
 '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': 0.2
+'clip_coef': 0.1
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1692328326.d15caa2368f0.1034.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fdf4450c998ed14a2d23766c97a906417879ea0dc9ba7ddf135f3d880409fde
+size 912333

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba9eba95178b8c1eeff91f1866f65cb2c8b1c65ceedc704e4da139555fb0614
+oid sha256:0e692ee0cd4d2725ed799378078eb0f71820fc09bc716ed9ec31738f7537c439
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -140.85198666337712, "std_reward": 109.454559775424, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-17T17:31:54.323724"}
+{"env_id": "LunarLander-v2", "mean_reward": -25.852769265164607, "std_reward": 39.85167034512174, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-18T03:21:06.353737"}