BML4

when you try something new

• Exploration

• Refuse to try anything different
• Avoid new things at all costs
• Exploitation

An active _______ is free to decide what actions to take because it does not have a fixed policy that determines its behavior.

Which of the following is NOT an element of Reinforcement Learning?

• A policy

• A reward function

• A value function

• A behavior

The same action is produced by the policy (π) at any state.

It is learning what to do (i.e. how to map situations to actions), so as to maximize a numerical reward signal.

• Supervised ML

• Unsupervised ML

• Reinforcement Learning

• None

________ learning involves learning with fixed policy, the task here is to learn the utilities of states (or state-action pairs);

In this policy, probability determines the produced action.

when you keep doing what you were doing

• Exploration

• Change your actions or behavior
• Take a break from what you were doing
• Exploitation

What is not part of the group?

• Environment

• Perception

• Guide

• Action

It is also called as the utility function.