Menu
Home
People
Places
Arts
History
Plants & Animals
Science
Life & Culture
Technology
Reference.org
Proximal policy optimization
open-in-new
<p>Proximal policy optimization (PPO) is a <a href="/facts/Reinforcement_learning/NrgPPS0Q">reinforcement learning</a> (RL) algorithm for training an <a href="/facts/Artificial_intelligence/lJGauQwX">intelligent agent</a>. Specifically, it is a <a href="/facts/Reinforcement_learning/NrgPPS0Q">policy gradient method</a>, often used for <a href="/facts/Deep_reinforcement_learning/9np68cqu">deep RL</a> when the policy network is very large. </p>