slides_lecture09.pdf - Lecture 9 Planning and Learning Lei Zhang Columbia University Lecture 9 – Learning Planning 1 Outline • Monte Carlo Tree

slides_lecture09.pdf - Lecture 9 Planning and Learning Lei...

This preview shows page 1 - 9 out of 31 pages.

Lecture 9: Planning and Learning Lei Zhang Columbia University 1 Lecture 9 – Learning & Planning
Image of page 1
Outline Monte Carlo Tree Search Model-based Planning Integrating Learning and Planning Columbia University 2 *materials are modified from David Silver’s RL lecture notes Lecture 9 – Learning & Planning
Image of page 2
Outline Monte Carlo Tree Search Model-based Planning Integrating Learning and Planning Columbia University 3 Lecture 9 – Learning & Planning
Image of page 3
Model-Based RL Revisited Model is known, but curse of dimensionality Each sweeping over states using DP is computationally costly. Game “GO” has high move and state complexity: States: 10^170 Studied for decades What can we do …. Columbia University Lecture 9 – Learning & Planning 4
Image of page 4
Rules of GO Columbia University Lecture 9 – Learning & Planning 5
Image of page 5
Position Evaluation in GO Columbia University Lecture 9 – Learning & Planning 6
Image of page 6
Simple Monte-Carlo Search Columbia University Lecture 9 – Learning & Planning 7
Image of page 7
Monte Carlo Tree Search (MCTS) Columbia University Lecture 9 – Learning & Planning 8 A method for finding optimal decisions by taking random samples and building a search tree according to the results Profound impact on AI MCTS includes four steps:
Image of page 8
Image of page 9

You've reached the end of your free preview.

Want to read all 31 pages?

  • Fall '17
  • Chong Li

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern

Stuck? We have tutors online 24/7 who can help you get unstuck.
A+ icon
Ask Expert Tutors You can ask You can ask You can ask (will expire )
Answers in as fast as 15 minutes
A+ icon
Ask Expert Tutors