Policy Iteration

Fact

An RL method that scores a policy, improves it, then repeats.

In Plain Words

Policy Iteration is a basketball coach at practice. First run the play. Then fix the ugly part.

In AI, it scores the current policy. Then it improves the policy and repeats. It is common in RL planning with a known model.

Related Concepts

• Reinforcement Learning
• Markov Decision Process
• Bellman Equation
• Value Iteration

RL
Policy Iteration is a classic RL method for finding better decisions.

MDP
Policy Iteration usually uses an MDP to define states, actions, and rewards.

Bellman Equation
Policy evaluation uses the Bellman Eq to compute values.

Value Iteration
Policy Iteration has the same goal as Value Iteration, but it separates scoring and improving.