Video Converter
Audio Converter
Image Converter
PDF Converter
File Compressor
reinforcement learning

Reinforcement learning Yifeng Tao School of Computer Science - PowerPoint PPT Presentation

Apr 15, 2023 •348 likes •645 views

Introduction to Machine Learning Reinforcement learning Yifeng Tao School of Computer Science Carnegie Mellon University Slides adapted from Matt Gormley, Eric Xing Yifeng Tao Carnegie Mellon University 1 Learning Paradigms [Slide from Matt

  1. Introduction to Machine Learning Reinforcement learning Yifeng Tao School of Computer Science Carnegie Mellon University Slides adapted from Matt Gormley, Eric Xing Yifeng Tao Carnegie Mellon University 1

  2. Learning Paradigms [Slide from Matt Gormley ] Yifeng Tao Carnegie Mellon University 2

  3. Examples of Reinforcement Learning [Slide from Matt Gormley ] Yifeng Tao Carnegie Mellon University 3

  4. Robot in a room [Slide from Eric Xing ] Yifeng Tao Carnegie Mellon University 4

  5. History of Reinforcement Learning o Roots in the psychology of animal learning (Thorndike,1911). o Another independent thread was the problem of optimal control, and its solution using dynamic programming (Bellman, 1957). o Idea of temporal difference learning (on-line method), e.g., playing board games (Samuel, 1959). o A major breakthrough was the discovery of Q-learning (Watkins, 1989). [Slide from Eric Xing ] Yifeng Tao Carnegie Mellon University 5

  6. What is special about RL? [Slide from Eric Xing ] Yifeng Tao Carnegie Mellon University 6

  7. Elements of RL [Slide from Eric Xing ] Yifeng Tao Carnegie Mellon University 7

  8. Policy o Reward for each step: -0.1 o Reward for each step -2 [Slide from Eric Xing ] Yifeng Tao Carnegie Mellon University 8

  9. The Precise Goal [Slide from Eric Xing ] Yifeng Tao Carnegie Mellon University 9

  10. Reinforcement Learning o Train a policy to maximize the discounted, cumulative reward R t0 : o γ : should be a constant between 0 and 1 o Bellman equation (deterministic): o Bellman equation (stochastic): [Slide from Matt Gormley ] Yifeng Tao Carnegie Mellon University 10

  11. Value Iteration [Slide from Matt Gormley ] Yifeng Tao Carnegie Mellon University 11

  12. Value Iteration Convergence [Slide from Matt Gormley ] Yifeng Tao Carnegie Mellon University 12

  13. Example: Robot Localization [Slide from Matt Gormley ] Yifeng Tao Carnegie Mellon University 13

  14. Value Iteration Variants o Variant 1: w/ Q(s,a) table à o Variant 2: w/o Q(s,a) table [Slide from Matt Gormley ] Yifeng Tao Carnegie Mellon University 14

  15. Synchronous vs. Asynchronous Value Iteration [Slide from Matt Gormley ] Yifeng Tao Carnegie Mellon University 15

  16. Value Iteration Convergence [Slide from Matt Gormley ] Yifeng Tao Carnegie Mellon University 16

  17. Policy Iteration [Slide from Matt Gormley ] Yifeng Tao Carnegie Mellon University 17

  18. Policy Iteration [Slide from Matt Gormley ] Yifeng Tao Carnegie Mellon University 18

  19. Value Iteration vs. Policy Iteration [Slide from Matt Gormley ] Yifeng Tao Carnegie Mellon University 19

  20. Deep Q-Learning [Slide from Matt Gormley ] Yifeng Tao Carnegie Mellon University 20

  21. TD Gammon à Alpha Go [Slide from Matt Gormley ] Yifeng Tao Carnegie Mellon University 21

  22. Playing Atari with Deep RL [Slide from Matt Gormley ] Yifeng Tao Carnegie Mellon University 22

  23. Deep Q-Network (DQN) algorithm o Goal: train Q(s, a) to fit the unknown reward (Q) function. o Then, best policy: o Bellman equation: o Temporal difference error: o Huber loss: o B : a batch of transitions, sampled from the replay memory [Slide from https://pytorch.org/tutorials/intermediate/reinforcement_q_learning.html ] Yifeng Tao Carnegie Mellon University 23

  24. Experience Replay [Slide from Matt Gormley ] Yifeng Tao Carnegie Mellon University 24

  25. Alpha Go [Slide from Matt Gormley ] Yifeng Tao Carnegie Mellon University 25

  26. Constructing Genetic Association Database [Slide from Wang et al. ] Yifeng Tao Carnegie Mellon University 26

  27. Constructing Genetic Association Database [Slide from Wang et al. ] Yifeng Tao Carnegie Mellon University 27

  28. Take home message o Reward, value, and policy in reinforcement learning o Value iteration and convergence guarantee o Policy iteration o Deep Q-learning uses neural network to approximate Q-functions Yifeng Tao Carnegie Mellon University 28

  29. References o Matt Gormley. 10601 Introduction to Machine Learning: http://www.cs.cmu.edu/~mgormley/courses/10601/index.html o Eric Xing, Tom Mitchell. 10701 Introduction to Machine Learning: http://www.cs.cmu.edu/~epxing/Class/10701-06f/ o Adam Paszke. Reinforcement Learning (DQN) Tutorial: https://pytorch.org/tutorials/intermediate/reinforcement_q_learning.ht ml o Haohan Wang et al. 2019: Automatic Human-like Mining and Constructing Reliable Genetic Association Database with Deep Reinforcement Learning Yifeng Tao Carnegie Mellon University 29

Recommend

Reinforcement Learning AIMA Chapters: 21.1, 21.2, 21.3. Sutton and Barto, Reinforcement Learning:

Reinforcement Learning AIMA Chapters: 21.1, 21.2, 21.3. Sutton and Barto, Reinforcement Learning:

Reinforcement Learning Reinforcement Learning AIMA Chapters: 21.1, 21.2, 21.3. Sutton and Barto, Reinforcement Learning: an Introduction, 2nd Edition: Chapters 6 (6.1 6.5) Outline Reinforcement Learning Reinforcement Learning: the

594 views • 27 slides
Reinforcement Learning Timothy Chou Charlie Tong Vincent Zhuang April 19, 2016 Reinforcement

Reinforcement Learning Timothy Chou Charlie Tong Vincent Zhuang April 19, 2016 Reinforcement

Reinforcement Learning Q-Learning Deep Q-Learning on Atari Reinforcement Learning Timothy Chou Charlie Tong Vincent Zhuang April 19, 2016 Reinforcement Learning Q-Learning Deep Q-Learning on Atari Table of Contents Reinforcement Learning

943 views • 63 slides
RL Overview of topics About Reinforcement Learning The Reinforcement Learning Problem

RL Overview of topics About Reinforcement Learning The Reinforcement Learning Problem

Introduction to Reinforcement Learning RL Overview of topics About Reinforcement Learning The Reinforcement Learning Problem Inside an RL agent Temporal difference learning Many faces of Reinforcement Learning What is

556 views • 35 slides
Reinforcement Learning UMaine COS 470/570 Introduction to AI Why reinforcement learning?

Reinforcement Learning UMaine COS 470/570 Introduction to AI Why reinforcement learning?

Reinforcement Learning<br/><br/> 4/25/19, 8*06 PM Reinforcement Learning<br/><br/> 4/25/19, 8*06 PM Reinforcement Learning UMaine COS 470/570 Introduction to AI Why reinforcement learning? Spring 2019 Created:

373 views • 15 slides
Reinforcement Learning Reinforcement Learning Reinforcement Learning in a nutshell g Imagine

Reinforcement Learning Reinforcement Learning Reinforcement Learning in a nutshell g Imagine

Reinforcement Learning Reinforcement Learning Reinforcement Learning in a nutshell g Imagine playing a new game whose rules you dont know; after a hundred or so moves your don t know; after a hundred or so moves, your opponent announces, You

512 views • 30 slides
Safe Reinforcement Learning Philip S. Thomas Stanford CS234: Reinforcement Learning, Guest

Safe Reinforcement Learning Philip S. Thomas Stanford CS234: Reinforcement Learning, Guest

Safe Reinforcement Learning Philip S. Thomas Stanford CS234: Reinforcement Learning, Guest Lecture May 24, 2017 Lecture overview What makes a reinforcement learning algorithm safe ? Notation Creating a safe reinforcement learning

1.43k views • 88 slides
Reinforcement Learning and Simulation-Based Search David Silver Reinforcement Learning and

Reinforcement Learning and Simulation-Based Search David Silver Reinforcement Learning and

Reinforcement Learning and Simulation-Based Search Reinforcement Learning and Simulation-Based Search David Silver Reinforcement Learning and Simulation-Based Search Outline 1 Reinforcement Learning 2 Simulation-Based Search 3 Planning Under

426 views • 20 slides
Introduction to Reinforcement Learning Kevin Chen and Zack Khan Lecture 1: Introduction to

Introduction to Reinforcement Learning Kevin Chen and Zack Khan Lecture 1: Introduction to

Lecture 1: Introduction to Reinforcement Learning Introduction to Reinforcement Learning Kevin Chen and Zack Khan Lecture 1: Introduction to Reinforcement Learning Outline 1. Course Logistics 2. What is Reinforcement Learning? 3.

932 views • 67 slides
CS885 Reinforcement Learning Module 2: June 6, 2020 Maximum Entropy Reinforcement Learning

CS885 Reinforcement Learning Module 2: June 6, 2020 Maximum Entropy Reinforcement Learning

CS885 Reinforcement Learning Module 2: June 6, 2020 Maximum Entropy Reinforcement Learning Haarnoja, Tang et al. (2017) Reinforcement Learning with Deep Energy Based Policies, ICML . Haarnoja, Zhou et al. (2018) Soft Actor-Critic: Off-Policy

685 views • 24 slides
Introduction to Reinforcement Learning and Q-Learning Skyler Seto (ss3349) May 2, 2016 Skyler

Introduction to Reinforcement Learning and Q-Learning Skyler Seto (ss3349) May 2, 2016 Skyler

Reinforcement Learning and Markov Decision Process Q-Learning Q-Learning Convergence Introduction to Reinforcement Learning and Q-Learning Skyler Seto (ss3349) May 2, 2016 Skyler Seto (ss3349) Introduction to Reinforcement Learning and

567 views • 27 slides
7. Motor Control and Reinforcement Learning Outline A. Action Selection and Reinforcement B.

7. Motor Control and Reinforcement Learning Outline A. Action Selection and Reinforcement B.

7. Motor Control and Reinforcement Learning Outline A. Action Selection and Reinforcement B. Temporal Difference Reinforcement Learning C. PVLV Model D. Cerebellum and Error-driven Learning 2/23/18 COSC 494/594 CCN 2 Sensory-Motor Loop

795 views • 56 slides
1 Deep Reinforcement Learning Qianqian Li, Nayeon Koong, Langtian He What is deep reinforcement

1 Deep Reinforcement Learning Qianqian Li, Nayeon Koong, Langtian He What is deep reinforcement

1 Deep Reinforcement Learning Qianqian Li, Nayeon Koong, Langtian He What is deep reinforcement learning? Agent/Actor + Action + Environment + State + Reward How does reinforcement learning work?

807 views • 31 slides
Introduction CSCE CSCE 496/896 496/896 Lecture 7: Lecture 7: Reinforcement Reinforcement

Introduction CSCE CSCE 496/896 496/896 Lecture 7: Lecture 7: Reinforcement Reinforcement

Introduction CSCE CSCE 496/896 496/896 Lecture 7: Lecture 7: Reinforcement Reinforcement CSCE 496/896 Lecture 7: Learning Learning Consider learning to choose actions, e.g., Stephen Scott Reinforcement Learning Stephen Scott Robot

437 views • 9 slides
CSC2621 Topics in Robotics Reinforcement Learning in Robotics Week 11: Hierarchical Reinforcement

CSC2621 Topics in Robotics Reinforcement Learning in Robotics Week 11: Hierarchical Reinforcement

CSC2621 Topics in Robotics Reinforcement Learning in Robotics Week 11: Hierarchical Reinforcement Learning Animesh Garg Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning Richard S. Sutton , Doina

2.19k views • 29 slides
Path following with reinforcement learning for autonomous cars - Mozzam Motiwala (IAS) Index

Path following with reinforcement learning for autonomous cars - Mozzam Motiwala (IAS) Index

Path following with reinforcement learning for autonomous cars - Mozzam Motiwala (IAS) Index Basics of Reinforcement Learning Model Based vs Model Free Reinforcement Learning Autonomous Car collision avoidance What is Reinforcement

714 views • 24 slides
Machine Learning for NLP Reinforcement learning Aurlie Herbelot 2019 Centre for Mind/Brain

Machine Learning for NLP Reinforcement learning Aurlie Herbelot 2019 Centre for Mind/Brain

Machine Learning for NLP Reinforcement learning Aurlie Herbelot 2019 Centre for Mind/Brain Sciences University of Trento 1 Introduction 2 Reinforcement learning: intuition Reinforcement learning: like learning to ride a bicycle.

1.19k views • 58 slides
Banking Dynamics and Capital Regulation Jos Vctor Ros Rull Tamon Takamura Yaz Terajima

Banking Dynamics and Capital Regulation Jos Vctor Ros Rull Tamon Takamura Yaz Terajima

Banking Dynamics and Capital Regulation Jos Vctor Ros Rull Tamon Takamura Yaz Terajima Penn, CAERP, UCL Bank of Canada Bank of Canada University of Michigan, March 28, 2018 WORK IN PROGRESS Capital Buffers as a form of Regulation

1.76k views • 174 slides
gsmws An Opportunity for Rural Cellular Service Shaddi Hasan, Kurtis Heimerl, Kate Harrison,

gsmws An Opportunity for Rural Cellular Service Shaddi Hasan, Kurtis Heimerl, Kate Harrison,

gsmws An Opportunity for Rural Cellular Service Shaddi Hasan, Kurtis Heimerl, Kate Harrison, Kashif Ali, Sean Roberts, Anant Sahai, Eric Brewer Shaddi Hasan UC Berkeley TIER/Endaga Thanks to... Tapan Parikh Peter Bloom, Ciaby, and

1.07k views • 86 slides
1 Prof. S. Ben-Yaakov , DC-DC Converters [1-4] Example (Cont.) % = 50 % It is 100W ! The

1 Prof. S. Ben-Yaakov , DC-DC Converters [1-4] Example (Cont.) % = 50 % It is 100W ! The

Prof. S. Ben-Yaakov , DC-DC Converters [1-1] The problem of Power Conversion Electricity Electricity Power AC-DC Rectifier Conversion DC-DC Power Type A Type B converter Uniderectional Power DC-AC Inverter Or AC-AC

391 views • 5 slides
NARUC CENTER FOR PARTNERSHIPS AND INNOVATION INNOVATION WEBINAR SERIES DECEMBER 19, 2019 DREAM

NARUC CENTER FOR PARTNERSHIPS AND INNOVATION INNOVATION WEBINAR SERIES DECEMBER 19, 2019 DREAM

NARUC CENTER FOR PARTNERSHIPS AND INNOVATION INNOVATION WEBINAR SERIES DECEMBER 19, 2019 DREAM MACHINE: AFTER THE RESEARCH & DEVELOPMENT (R&D) ECOSYSTEM DEPLOYMENT AND COMMERCIALIZATION WHAT IS NARUC The National Association of

441 views • 16 slides
Reinforcement Learning for NLP Graham Neubig Site https://phontron.com/class/nn4nlp2019/ What

Reinforcement Learning for NLP Graham Neubig Site https://phontron.com/class/nn4nlp2019/ What

CS11-747 Neural Networks for NLP Reinforcement Learning for NLP Graham Neubig Site https://phontron.com/class/nn4nlp2019/ What is Reinforcement Learning? Learning where we have an environment X ability to make actions A get a

602 views • 29 slides
Reinforcement Learning-Based SLC Cache Technique for Enhancing SSD Write Performance Sangjin Yoo

Reinforcement Learning-Based SLC Cache Technique for Enhancing SSD Write Performance Sangjin Yoo

1 18 Reinforcement Learning-Based SLC Cache Technique for Enhancing SSD Write Performance Sangjin Yoo and Dongkun Shin Sungkyunkwan University, Korea newlandlord@skku.edu, dongkun@skku.edu Sungkyunkwan university Hotstorage20

356 views • 18 slides
Reinforcemen t Learning Read Chapter Exercises

Reinforcemen t Learning Read Chapter Exercises

Reinforcemen t Learning Read Chapter Exercises Con trol learning Con trol p olici es that c ho ose optimal actions Q learning

551 views • 20 slides
Reinforcement Learning: Part 2 Chris Watkins Department of Computer Science Royal Holloway,

Reinforcement Learning: Part 2 Chris Watkins Department of Computer Science Royal Holloway,

Reinforcement Learning: Part 2 Chris Watkins Department of Computer Science Royal Holloway, University of London July 27, 2015 1 TD(0) learning Define the temporal difference prediction error t = r t + V ( s t +1 ) V ( s t ) Agent

438 views • 31 slides

More recommend

Explore More Topics

Stay informed with curated content and fresh updates.

animals pets art culture automotive transportation business finance computer internet construction architecture education-career electronics communication

Logo Sambuz

Unleash a World of Digital Possibilities—Browse, Share, and Explore Content Without Boundaries

Useful Links

About Us Privacy Services FAQ's Contact

Newsletter

Stay Informed & Inspired—Subscribe for the Latest Updates, Tips, and Exclusive Content Directly to Your Inbox.

Mail Us

mail@sambuz.com

2026 SAMBUZ, All right reserved.