Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 148.33 +/- 113.19
+      value: 192.29 +/- 107.12
       name: mean_reward
       verified: false
 ---
@@ -30,7 +30,7 @@ model-index:
   ```python
   {'exp_name': 'ppo'
 'gym_id': 'LunarLander-v2'
-'learning_rate': 0.00025
+'learning_rate': 0.0003
 'seed': 1
 'total_timesteps': 10000000
 'torch_deterministic': True
@@ -39,12 +39,12 @@ model-index:
 'wandb_project_name': 'cleanRL'
 'wandb_entity': None
 'capture_video': True
-'num_envs': 4
-'num_steps': 128
+'num_envs': 16
+'num_steps': 32
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
+'gamma': 0.999
+'gae_lambda': 0.98
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e5ef55d2fe6ca94fb96997fe35dfefccb710fec4db4b401a193329340ebe592
+oid sha256:79a1921dcce677b50cbd5489f2e7d4bf9b11b076912d32a7d13315f899d611ab
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 148.32791376582335, "std_reward": 113.19260302497052, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-29T14:26:01.547299"}
+{"env_id": "LunarLander-v2", "mean_reward": 192.2911155606413, "std_reward": 107.12237244180385, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-29T16:23:26.734859"}