Push agent to 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:
@@ -16,22 +17,43 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 255.63 +/- 21.44
+      value: -146.44 +/- 110.06
       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).
+    # PPO Agent Playing LunarLander-v2
 
-## Usage (with Stable-baselines3)
-TODO: Add your code
+    This is a trained model of a PPO agent playing LunarLander-v2.
 
-
-```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
-
-...
-```
+    # Hyperparameters
+    {'exp_name': 'ppo'
+'seed': 1
+'torch_deterministic': True
+'cuda': False
+'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': 'swritchie/ppo-LunarLander-v2'
+'batch_size': 512
+'minibatch_size': 128}
+    

logs/events.out.tfevents.1717509841.728dbb590918.12580.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7c8fd08a30394fa545c94e49e2e030027a56238c871554a55ccd9b69e08f7af
+size 109093

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e6499ce165096e04b63c5d498a1385bf2d14e8c62e7fa73e34970f015796724
+size 42898

results.json

@@ -1 +1 @@
-{"mean_reward": 255.62533459999995, "std_reward": 21.443103204252914, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-20T15:38:49.444228"}
+{"env_id": "LunarLander-v2", "mean_reward": -146.4400850970961, "std_reward": 110.05527794801911, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-04T14:04:37.768627"}