first commit

README.md

@@ -1,3 +1,61 @@
 ---
-license: apache-2.0
+tags:
+- LunarLander-v2
+- ppo
+- deep-reinforcement-learning
+- reinforcement-learning
+- custom-implementation
+- deep-rl-course
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: -154.83 +/- 149.67
+      name: mean_reward
+      verified: false
 ---
+
+  # 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': 5000
+'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': 'ThomasSimonini/cleanrlTESTPPO2'
+'batch_size': 512
+'minibatch_size': 128}
+  ```
+  

logs/events.out.tfevents.1676474570.027365e45aa0.2659.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8a40fcc90f734b17e9a6102beb9a1c61729ececf599f039af8f33337d7df82f
+size 10851

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3fc8069cb3aa45bddaee8c0f699e6f200ae641ebc5fc9d4e13b2996ca80f4fc
+size 42597

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -154.83228420801055, "std_reward": 149.67086911054324, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-15T15:23:05.364435"}