Downloads · 30 days
0
PPO_Lunar_Lander
Farbum/PPO_Lunar_Lander
PPO_Lunar_Lander is a reinforcement learning model from Farbum. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product.
This is a trained model of a PPO agent playing LunarLander-v2.
Access
Public
Updated Apr 2, 2024
Repo size
417 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.mp480.8 KB · 60%
At a glance
- Task
- Reinforcement Learning
- Access
- Public
- Created
- Dec 2, 2023
- Updated
- Apr 2, 2024
- SHA
- 958cf565
Model card
From the Hugging Face model README
PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
Hyperparameters
hp_seed: 5678<br />hp_total_timesteps: 500000<br />hp_learning_rate: 0.001<br />hp_min_learning_rate: 1.5e-06<br />hp_num_envs: 12<br />hp_num_steps: 256<br />hp_anneal_lr: True<br />hp_gae: True<br />hp_gamma: 0.99<br />hp_gae_lambda: 0.95<br />hp_minibatch_size: 256<br />hp_update_epochs: 4<br />hp_norm_adv: True<br />hp_clip_coef: 0.2<br />hp_clip_vloss: True<br />hp_ent_coef: 0.01<br />hp_vf_coef: 0.5<br />hp_max_grad_norm: 0.5<br />hp_target_kl: None
- Task
- Reinforcement Learning
- Created
- Dec 2, 2023
- Updated
- Apr 2, 2024