CS代考 CSC 311: Introduction to Machine Learning – cscodehelp代写

CSC 311: Introduction to Machine Learning
Lecture 8 – Reinforcement Learning
University of Toronto
Intro ML (UofT) CSC311-Lec8 1 / 46

Reinforcement Learning Problem
In supervised learning, the problem is to predict an output t given an input x.
But often the ultimate goal is not to predict, but to make decisions, i.e., take actions.
In many cases, we want to take a sequence of actions, each of which affects the future possibilities, i.e., the actions have long-term
consequences.
learning-based approaches.
An agent observes the takes an action and with the goal of world its states changes achieving long-term
Reinforcement Learning Problem: An agent continually interacts with an environment. How should it choose its actions so that its long-term rewards
Reinforcement Learning Problem: An agent continually interacts with the
are maximizeedn?vironment. How should it choose its actions so that its long-term rewards are
maximized?
Intro ML (UofT) CSC311-Lec8 2 / 46
Also might be called:

Playing Games: Atari