Menu
Home
People
Places
Arts
History
Plants & Animals
Science
Life & Culture
Technology
Reference.org
Policy gradient method
open-in-new
<p>Policy gradient methods are a class of <a href="/facts/Reinforcement_learning/NrgPPS0Q">reinforcement learning</a> algorithms. </p><p>Policy gradient methods are a sub-class of policy optimization methods. Unlike value-based methods which learn a value function to derive a policy, policy optimization methods directly learn a <a href="/facts/Policy_function/Qh2gKSMH">policy function</a> π {\displaystyle \pi } that selects actions without consulting a value function. For policy gradient to apply, the policy function π θ {\displaystyle \pi _{\theta }} is parameterized by a differentiable parameter θ {\displaystyle \theta } . </p>