Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -10.97 +/- 59.31
+      value: 38.61 +/- 117.37
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
+'total_timesteps': 1000000
 'learning_rate': 0.0001
 'num_envs': 4
 'num_steps': 128
@@ -48,8 +48,8 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.2
-'clip_vloss': True
+'clip_coef': 0.5
+'clip_vloss': False
 'ent_coef': 0.01
 'vf_coef': 0.5
 'max_grad_norm': 0.5

logs/events.out.tfevents.1692005027.c14e1bfbd2c3.11189.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f993bfc3e1b67f2ab1619485da75482cc9c785ef66489b7f38e850ca85a3bba
+size 1312178

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba3bfc6accd9b3ad96a3109eeb65628ef460b5d85ae561451579bafda7bd2c5f
+oid sha256:80286643c9d8bca7a2adbac2ced3d6fc035f70028fafaa0474fab303e34fd61b
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -10.966958893174622, "std_reward": 59.3086053918031, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-14T09:22:10.491180"}
+{"env_id": "LunarLander-v2", "mean_reward": 38.61409593215818, "std_reward": 117.36882567256943, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-14T09:52:57.347255"}