Push agent to the Hub

README.md

@@ -1,10 +1,11 @@
 ---
-library_name: stable-baselines3
 tags:
 - LunarLander-v2
+- ppo
 - deep-reinforcement-learning
 - reinforcement-learning
-- stable-baselines3
+- custom-implementation
+- deep-rl-course
 model-index:
 - name: PPO
   results:
@@ -16,60 +17,45 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 239.92 +/- 20.79
+      value: -117.50 +/- 52.66
       name: mean_reward
       verified: false
 ---
 
-# **PPO** Agent playing **LunarLander-v2**
-This is a trained model of a **PPO** agent playing **LunarLander-v2**
-using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
-
-## Usage (with Stable-baselines3)
-
-```python
-#create enviroment
-env = gym.make('LunarLander-v2')
-
-#reset enviroment ot initial state
-env.reset()
-
-#create vectorized enviroment
-env = make_vec_env("LunarLander-v2", n_envs=16)
-
-#instanciate the agent
-#params: https://stable-baselines3.readthedocs.io/en/master/modules/ppo.html#parameters
-model = PPO('MlpPolicy',env,verbose=1,
-            learning_rate=0.0003,
-            # n_steps=2048,
-            n_steps=1024,
-            batch_size=64,
-            # n_epochs=10,
-            n_epochs=4,
-            # gamma=0.99,
-            gamma=0.999,
-            # gae_lambda=0.95,
-            gae_lambda=0.98,
-            clip_range=0.2,
-            clip_range_vf=None,
-            normalize_advantage=True,
-            # ent_coef=0.0,
-            ent_coef=0.01
-            # vf_coef=0.5,
-            # max_grad_norm=0.5,
-            # use_sde=False,
-            # sde_sample_freq=-1,
-            # target_kl=None,
-            # tensorboard_log=None,
-            # policy_kwargs=None,
-            # verbose=0,
-            # seed=seed,
-            # device='auto',
-            # _init_setup_model=True           
-            )
-
-#train model
-model.learn(total_timesteps=int(1e6))
-
-...
-```
+  # 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': 50000
+'learning_rate': 0.00025
+'num_envs': 4
+'num_steps': 128
+'anneal_lr': True
+'gae': True
+'gamma': 0.99
+'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': 'asuzuki/ppo-LunarLander-v2'
+'batch_size': 512
+'minibatch_size': 128}
+  ```
+  

logs/events.out.tfevents.1679474938.90299d310247.12985.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9ff66f44399111e639518ea1a13e95687b41108247d623bfbebf9b408da5c9b
+size 111160

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
+size 42597

results.json

@@ -1 +1 @@
-{"mean_reward": 239.92169866976738, "std_reward": 20.791617039010347, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-06T08:49:26.545362"}
+{"env_id": "LunarLander-v2", "mean_reward": -117.50342778410364, "std_reward": 52.664344272654795, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-22T08:49:47.440292"}