# Fast PPO Configuration
# Lower timestep count for quick iterations/testing.

learning_rate: 0.0005
total_timesteps: 1024
num_envs: 32
num_steps: 32
anneal_lr: 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: null