Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -70.42 +/- 96.68
+      value: -139.40 +/- 97.19
       name: mean_reward
       verified: false
 ---
@@ -25,6 +25,37 @@ model-index:
   # PPO Agent Playing LunarLander-v2
 
   This is a trained model of a PPO agent playing LunarLander-v2.
-
+    
   # Hyperparameters
+  ```python
+  {'exp_name': 'ppo'
+'seed': 1
+'torch_deterministic': True
+'cuda': True
+'track': False
+'wandb_project_name': 'cleanRL'
+'wandb_entity': None
+'capture_video': False
+'env_id': 'LunarLander-v2'
+'total_timesteps': 200000
+'learning_rate': 0.00025
+'num_envs': 4
+'num_steps': 128
+'anneal_lr': True
+'gae': True
+'gamma': 0.9999
+'gae_lambda': 0.95
+'num_minibatches': 4
+'update_epochs': 4
+'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': 'Retrial9842/ppo-cleanrl-LunarLander-v2'
+'batch_size': 512
+'minibatch_size': 128}
+  ```
   

logs/events.out.tfevents.1687756530.75b9c3b544af.5094.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e00c44f6785ee52cf05e06afce610ed842a1a70de28b744af59e87250d88e555
+size 390084

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5087b184aa63f2876f8eb7deafa1977279ee752dcc9888133e2078cee4523558
+oid sha256:eff8496529291926a87558bda56a121e7c9f18f1c69be69f79b47bba8d23c91c
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -70.41598321062779, "std_reward": 96.68479221687785, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-26T04:30:54.410825"}
+{"env_id": "LunarLander-v2", "mean_reward": -139.4041795012451, "std_reward": 97.19172667631562, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-26T05:18:49.950027"}