Push agent to the Hub

README.md

@@ -1,28 +1,62 @@
 ---
-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: 281.43 +/- 23.89
-      name: mean_reward
-    task:
+  - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
       name: LunarLander-v2
       type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: -185.98 +/- 75.59
+      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
+  {'f': '/root/.local/share/jupyter/runtime/kernel-92a40984-11d7-49e0-b473-b46995cf7df4.json'
+'exp_name': 'ppo_clean_rl'
+'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': 'Galeros/ppo-LunarLander-v2'
+'batch_size': 512
+'minibatch_size': 128}
+  ```
   

logs/events.out.tfevents.1682578478.e27bd58f3084.8026.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c9432f605260f58ce62e2f9d73c36ccd58d8785b65e2ab81bf01e776115a813
+size 110063

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a363dfe098933c96feb65ea5062a91e8aacf7448c05ac211c1404fb4e0f78d9
+size 42597

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a10e2fbfedf56c6fdadccbfbe23cf253a6ef5efd827d0ca1dd3acc946c3f5113
-size 231361
+oid sha256:8e0923f0d9f9b2843d8825dc43d1c06d0813b0615c518bc9c7e4100f708f3981
+size 22067

results.json

@@ -1 +1 @@
-{"mean_reward": 281.43437720458627, "std_reward": 23.892504554624935, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-29T21:31:39.071226"}
+{"env_id": "LunarLander-v2", "mean_reward": -185.98025561294372, "std_reward": 75.58581454440034, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-27T06:55:24.979382"}