Update README.md
Browse files
README.md
CHANGED
@@ -27,4 +27,4 @@ model-index:
|
|
27 |
This is a trained model of a PPO agent playing LunarLander-v2.
|
28 |
|
29 |
# Hyperparameters
|
30 |
-
|
|
|
27 |
This is a trained model of a PPO agent playing LunarLander-v2.
|
28 |
|
29 |
# Hyperparameters
|
30 |
+
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
|