Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 31.27 +/- 115.10
+      value: -178.11 +/- 96.59
       name: mean_reward
       verified: false
 ---
@@ -25,7 +25,7 @@ model-index:
   # PPO Agent Playing LunarLander-v2
 
   This is a trained model of a PPO agent playing LunarLander-v2.
-
+    
   # Hyperparameters
   ```python
   {'exp_name': 'ppo'
@@ -37,18 +37,18 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
-'learning_rate': 0.00025
+'total_timesteps': 100000
+'learning_rate': 0.0001
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
+'gamma': 0.999
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.2
+'clip_coef': 0.38
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1727704374.6b0a310582bf.6765.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75fa6997fb30544affa8dcc2931e5e962fb0bb5f9fa6e6a7bf7ad11da7b07810
+size 217485

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9a2f5da9739cd080252297480009c8939101f5219045009864dcb78b9e2c213
+oid sha256:d86c2d77e6039422971eda797255403d84cee8c3f9dae54ad4eb232692a1f0fa
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 31.27017484900832, "std_reward": 115.09811070185707, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-27T13:45:28.214268"}
+{"env_id": "LunarLander-v2", "mean_reward": -178.1143375782521, "std_reward": 96.59076690452741, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-30T13:54:24.087378"}