Push agent to the Hub

README.md

@@ -1,28 +1,61 @@
 ---
-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:
-  - metrics:
-    - type: mean_reward
-      value: 285.73 +/- 12.71
-      name: mean_reward
-    task:
+  - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
       name: LunarLander-v2
       type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: -180.06 +/- 101.13
+      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)
-  TODO: Add your code
+  # 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': 'sswt/ppo-LunarLander-v2'
+'batch_size': 512
+'minibatch_size': 128}
+  ```
   

logs/events.out.tfevents.1727355864.70c6f8ef8334.3341.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d686c6508cd0f1fec41d46cd3d0ec4fbfa86aa7a228f6c73246c4ac31b5003ad
+size 109717

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
+size 43026

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beefebc4eed2d4e3feb3bbc69577eaa4aa95be8561096183ee578b9d200ebadc
-size 193537
+oid sha256:5bba36351f2b4c2620f10e5504a133cda93916b7016c5a6d288e21a0796c98e6
+size 19419

results.json

@@ -1 +1 @@
-{"mean_reward": 285.73021263595433, "std_reward": 12.7050687730098, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-10T12:26:18.067777"}
+{"env_id": "LunarLander-v2", "mean_reward": -180.0636013297672, "std_reward": 101.13174976125232, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-26T13:05:09.508664"}