# Stable PPO Configuration
# Standard hyperparams with lower LR and larger batch.

learning_rate: 0.0001
total_timesteps: 10000000
num_envs: 100
num_steps: 256
anneal_lr: true
gamma: 0.99
gae_lambda: 0.95
num_minibatches: 8
update_epochs: 4
norm_adv: true
clip_coef: 0.1
clip_vloss: true
ent_coef: 0.01
vf_coef: 0.5
max_grad_norm: 0.5
target_kl: null