Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 169.13 +/- 64.55
+      value: 173.53 +/- 62.70
       name: mean_reward
       verified: false
 ---
@@ -27,4 +27,35 @@ model-index:
   This is a trained model of a PPO agent playing LunarLander-v2.
 
   # Hyperparameters
+  ```python
+  {'exp_name': 'ppo'
+'env_id': 'LunarLander-v2'
+'seed': 1
+'torch_deterministic': True
+'cuda': True
+'track': False
+'wandb_project_name': 'cleanRL'
+'wandb_entity': None
+'capture_video': False
+'learning_rate': 0.00025
+'total_timesteps': 1000000
+'num_envs': 4
+'num_steps': 1024
+'anneal_lr': True
+'gae': True
+'gamma': 0.99
+'gae_lambda': 0.98
+'num_minibatches': 4
+'update_epochs': 20
+'norm_adv': True
+'clip_coef': 0.2
+'clip_vloss': True
+'ent_coef': 0.01
+'vf_coef': 0.5
+'max_grad_norm': 0.5
+'target_kl': None
+'repo_id': 'rahil1206/test'
+'batch_size': 4096
+'minibatch_size': 1024}
+  ```
   

logs/events.out.tfevents.1714590436.DESKTOP-8JGD4UI.30952.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9db1ca6fcd1a149584840a894d1044d0ace993a47eccb873c804ba9e6afed0d
+size 341184

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 169.132462170396, "std_reward": 64.54639970119024, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-01T20:04:38.614431"}
+{"env_id": "LunarLander-v2", "mean_reward": 173.5291127904021, "std_reward": 62.697373599659564, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-01T20:37:14.171451"}