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:
@@ -16,22 +17,42 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 251.53 +/- 33.99
+      value: -172.07 +/- 103.51
       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
-
-
-```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
-
-...
-```
+This is a trained model of a PPO agent playing LunarLander-v2.
+    
+# Hyperparameters
+{'exp_name': 'ppo'
+'seed': 1
+'torch_deterministic': True
+'cuda': True
+'track': False
+'wandb_project_name': 'cleanRL'
+'wandb_entity': None
+'capture_video': True
+'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': 'mblond/ppo-LunarLander-v2'
+'batch_size': 512
+'minibatch_size': 128}

logs/events.out.tfevents.1751044415.530382669b66.8747.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a469b8c9c72a32495210e631ae36b247d6b2448977e7e959d27e562561f6a47
+size 110594

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e592fb92948eb720ebf65e9ba651a3ca7834e96ec574ac31ef975b4528652b8
+size 42898

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2b9e87eaf308c085215832d44b7fec9c3af576dab7606e26b40fc3bb15ff376
-size 166894
+oid sha256:896be16a00937e917ef2516da1b911e7e2fccd44ae16dc242fba800af78b959a
+size 20386

results.json

@@ -1 +1 @@
-{"mean_reward": 251.5253254, "std_reward": 33.991387921417015, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-26T13:52:20.945083"}
+{"env_id": "LunarLander-v2", "mean_reward": -172.0671650188312, "std_reward": 103.50686113042521, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-27T17:14:30.129460"}