The Multi-Armed Bandit Problem

Size: px
Start display at page:

Download "The Multi-Armed Bandit Problem"

Transcription

1 The Multi-Armed Bandit Problem Electrical and Computer Engineering December 7, 2013

2 Outline 1 2 Mathematical 3 Algorithm Upper Confidence Bound Algorithm

3 A/B Testing

4 Exploration vs. Exploitation Scientist View Explore new ideas Businessman View Exploit best idea found so far

5 Terminology pulling an arm = making a choice (which ad/color to display) reward/regret = measure of success (user-click, item-buy)

6 Problem Formulation Formulation K arms 1,, K Arm i gives reward distribution ν i (x), x [0, 1] with mean µ i. Think Bernoulli(p i ) ν i s unknown Finite time horizon (arm-pulls) n At time t, player chooses arm I t {1,, K}, the environment rewards g It,t ν It

7 Problem Formulation Formulation K arms 1,, K Arm i gives reward distribution ν i (x), x [0, 1] with mean µ i. Think Bernoulli(p i ) ν i s unknown Finite time horizon (arm-pulls) n At time t, player chooses arm I t {1,, K}, the environment rewards g It,t ν It

8 Problem Formulation Formulation K arms 1,, K Arm i gives reward distribution ν i (x), x [0, 1] with mean µ i. Think Bernoulli(p i ) ν i s unknown Finite time horizon (arm-pulls) n At time t, player chooses arm I t {1,, K}, the environment rewards g It,t ν It

9 Problem Formulation Formulation K arms 1,, K Arm i gives reward distribution ν i (x), x [0, 1] with mean µ i. Think Bernoulli(p i ) ν i s unknown Finite time horizon (arm-pulls) n At time t, player chooses arm I t {1,, K}, the environment rewards g It,t ν It

10 Problem Formulation Formulation K arms 1,, K Arm i gives reward distribution ν i (x), x [0, 1] with mean µ i. Think Bernoulli(p i ) ν i s unknown Finite time horizon (arm-pulls) n At time t, player chooses arm I t {1,, K}, the environment rewards g It,t ν It

11 Definitions Define i = arg max i=1,,k µ i µ = max i=1,,k µ i i = µ µ i T i (n) = n ½ It =i t=1 Cumulative regret ˆR n = n g i,t n t=1 g It,t t=1 Objective Find best arm Minimize expected regret R n = EˆR n = nµ E K T i (n)µ i = K i ET i (n) i=1 i=1

12 Definitions Define i = arg max i=1,,k µ i µ = max i=1,,k µ i i = µ µ i T i (n) = n ½ It =i t=1 Cumulative regret ˆR n = n g i,t n t=1 g It,t t=1 Objective Find best arm Minimize expected regret R n = EˆR n = nµ E K T i (n)µ i = K i ET i (n) i=1 i=1

13 Definitions Define i = arg max i=1,,k µ i µ = max i=1,,k µ i i = µ µ i T i (n) = n ½ It =i t=1 Cumulative regret ˆR n = n g i,t n t=1 g It,t t=1 Objective Find best arm Minimize expected regret R n = EˆR n = nµ E K T i (n)µ i = K i ET i (n) i=1 i=1

14 Definitions Define i = arg max i=1,,k µ i µ = max i=1,,k µ i i = µ µ i T i (n) = n ½ It =i t=1 Cumulative regret ˆR n = n g i,t n t=1 g It,t t=1 Objective Find best arm Minimize expected regret R n = EˆR n = nµ E K T i (n)µ i = K i ET i (n) i=1 i=1

15 Outline 1 2 Mathematical 3 Algorithm Upper Confidence Bound Algorithm

16 Clarification Objectively and Subjectively Best Options Objectively best: Which option is truly the best (as known to an oracle) Subjectively best: Which option has been best in the past? Exploitation vs. Exploration Exploitation: Choose the subjectively best arm Exploration: Choosing anything else

17 Clarification Objectively and Subjectively Best Options Objectively best: Which option is truly the best (as known to an oracle) Subjectively best: Which option has been best in the past? Exploitation vs. Exploration Exploitation: Choose the subjectively best arm Exploration: Choosing anything else

18 Algorithm 1 2 K Strategy = ǫ Scientist +(1 ǫ) Businessman At each time t With probability 1 ǫ, pick the subjectively best arm With probability ǫ K, pick a random arm

19 Probability of Selecting Best Arm Bernoulli arms with reward probabilities 0.1, 0.1, 0.1, 0.1, 0.9 Accuracy of the Epsilon Greedy Algorithm Probability of Selecting Best Arm Epsilon ǫ = 0.1(Businessman) Learns slowly Does well at the end ǫ = 0.5(Scientist) Learns quickly Doesn t exploit at the end Time

20 Theoretical guarantee Weakness - ǫ constant: Solution - annealing Theoretical Guarantee (Auer, Cesa-Bianchi, Fischer, 2002) ) Let = min i: i >0 i and consider ǫ t = min( 6K 2 t, 1 When t 6K, the probability of choosing a suboptimal arm 2 i is bounded by C, for some constant C > 0. 2 t As a consequence, E[T i (n)] C log n and 2 R n i: i >0 C i 2 log n logarithmic regret.

21 Theoretical guarantee Weakness - ǫ constant: Solution - annealing Theoretical Guarantee (Auer, Cesa-Bianchi, Fischer, 2002) ) Let = min i: i >0 i and consider ǫ t = min( 6K 2 t, 1 When t 6K, the probability of choosing a suboptimal arm 2 i is bounded by C, for some constant C > 0. 2 t As a consequence, E[T i (n)] C log n and 2 R n i: i >0 C i 2 log n logarithmic regret.

22 Theoretical guarantee Weakness - ǫ constant: Solution - annealing Theoretical Guarantee (Auer, Cesa-Bianchi, Fischer, 2002) ) Let = min i: i >0 i and consider ǫ t = min( 6K 2 t, 1 When t 6K, the probability of choosing a suboptimal arm 2 i is bounded by C, for some constant C > 0. 2 t As a consequence, E[T i (n)] C log n and 2 R n i: i >0 C i 2 log n logarithmic regret.

23 Weakness of ǫ Greedy Exploration insensitive to relative performance levels Two arms with rewards 0.9 and 0.1 Two arms with rewards 0.15 and 0.1 Solution -

24 Idea: P(arm 1) = ˆµ 1 ˆµ 1 + ˆµ 2 P(arm 2) = ˆµ 2 ˆµ 1 + ˆµ 2 Variant: P(arm 1) = P(arm 2) = e µ ˆ 1 T e µ ˆ 1 T e µ ˆ 1 T + e µ ˆ 2 T e µ ˆ 2 T + e µ ˆ 2 T T : Pure exploration T = 0 : Pure exploitation

25 Idea: P(arm 1) = ˆµ 1 ˆµ 1 + ˆµ 2 P(arm 2) = ˆµ 2 ˆµ 1 + ˆµ 2 Variant: P(arm 1) = P(arm 2) = e µ ˆ 1 T e µ ˆ 1 T e µ ˆ 1 T + e µ ˆ 2 T e µ ˆ 2 T + e µ ˆ 2 T T : Pure exploration T = 0 : Pure exploitation

26 Weakness of Softmax Doesn t use confidence ˆp 1 = 0.15 after 100 plays, ˆp 2 = 0.1 after 100 plays. ˆp 1 = 0.15 after 100K plays, ˆp 2 = 0.1 after 100K plays. Solution - (Upper Confidence Bound) Algorithm

27 Algorithm Optimism in the Face of Uncertainty At time t, construct most optimistic estimate for each arm V i,t 1 = ˆµ i,t log t T i (t 1) Play arm with max upper { bound. } i.e. play I t arg max Vi,t 1 i {1,,K} Proof based on Hoeffding s inequality

28 Algorithm Optimism in the Face of Uncertainty At time t, construct most optimistic estimate for each arm V i,t 1 = ˆµ i,t log t T i (t 1) Play arm with max upper { bound. } i.e. play I t arg max Vi,t 1 i {1,,K} Proof based on Hoeffding s inequality

29 Algorithm Optimism in the Face of Uncertainty At time t, construct most optimistic estimate for each arm V i,t 1 = ˆµ i,t log t T i (t 1) Play arm with max upper { bound. } i.e. play I t arg max Vi,t 1 i {1,,K} Proof based on Hoeffding s inequality

30 Algorithm Optimism in the Face of Uncertainty At time t, construct most optimistic estimate for each arm V i,t 1 = ˆµ i,t log t T i (t 1) Play arm with max upper { bound. } i.e. play I t arg max Vi,t 1 i {1,,K} Proof based on Hoeffding s inequality

31 Results Accuracy of the 1 Algorithm 1.00 Probability of Selecting Best Arm Time

32 Theoretical Guarantee Regret Bound (Auer, Cesa-Bianchi, Fischer, 2002) [ ] ( ) ( ) ( ) R n log n K i + 1+ π2 3 i i:µ i <µ i=1 Lower bound (Lai and Rubbins 1985) Asymptotic total regret is at least logarithmic in number of steps lim R n log n i n KL(ν i ν ) i: i >0

33 Theoretical Guarantee Regret Bound (Auer, Cesa-Bianchi, Fischer, 2002) [ ] ( ) ( ) ( ) R n log n K i + 1+ π2 3 i i:µ i <µ i=1 Lower bound (Lai and Rubbins 1985) Asymptotic total regret is at least logarithmic in number of steps lim R n log n i n KL(ν i ν ) i: i >0

34 Comparison Accuracy of Different Probability of Selecting Best Arm 0.50 Algorithm Annealing epsilon Greedy 1 Annealing Softmax Time

35 Summary 1 2 Mathematical 3 Algorithm Upper Confidence Bound Algorithm

36 References White, John. Bandit for Website Optimization. O Reilly, Auer, Peter, Nicolo Cesa-Bianchi, and Paul Fischer. "Finite-time analysis of the multiarmed bandit problem." Machine learning (2002):

Bandit Algorithms. Zhifeng Wang ... Department of Statistics Florida State University

Bandit Algorithms. Zhifeng Wang ... Department of Statistics Florida State University Bandit Algorithms Zhifeng Wang Department of Statistics Florida State University Outline Multi-Armed Bandits (MAB) Exploration-First Epsilon-Greedy Softmax UCB Thompson Sampling Adversarial Bandits Exp3

More information

Advanced Machine Learning

Advanced Machine Learning Advanced Machine Learning Bandit Problems MEHRYAR MOHRI MOHRI@ COURANT INSTITUTE & GOOGLE RESEARCH. Multi-Armed Bandit Problem Problem: which arm of a K-slot machine should a gambler pull to maximize his

More information

Introduction to Bandit Algorithms. Introduction to Bandit Algorithms

Introduction to Bandit Algorithms. Introduction to Bandit Algorithms Stochastic K-Arm Bandit Problem Formulation Consider K arms (actions) each correspond to an unknown distribution {ν k } K k=1 with values bounded in [0, 1]. At each time t, the agent pulls an arm I t {1,...,

More information

Bandit models: a tutorial

Bandit models: a tutorial Gdt COS, December 3rd, 2015 Multi-Armed Bandit model: general setting K arms: for a {1,..., K}, (X a,t ) t N is a stochastic process. (unknown distributions) Bandit game: a each round t, an agent chooses

More information

An Optimal Bidimensional Multi Armed Bandit Auction for Multi unit Procurement

An Optimal Bidimensional Multi Armed Bandit Auction for Multi unit Procurement An Optimal Bidimensional Multi Armed Bandit Auction for Multi unit Procurement Satyanath Bhat Joint work with: Shweta Jain, Sujit Gujar, Y. Narahari Department of Computer Science and Automation, Indian

More information

The Multi-Armed Bandit Problem

The Multi-Armed Bandit Problem Università degli Studi di Milano The bandit problem [Robbins, 1952]... K slot machines Rewards X i,1, X i,2,... of machine i are i.i.d. [0, 1]-valued random variables An allocation policy prescribes which

More information

Multi-armed bandit models: a tutorial

Multi-armed bandit models: a tutorial Multi-armed bandit models: a tutorial CERMICS seminar, March 30th, 2016 Multi-Armed Bandit model: general setting K arms: for a {1,..., K}, (X a,t ) t N is a stochastic process. (unknown distributions)

More information

Lecture 19: UCB Algorithm and Adversarial Bandit Problem. Announcements Review on stochastic multi-armed bandit problem

Lecture 19: UCB Algorithm and Adversarial Bandit Problem. Announcements Review on stochastic multi-armed bandit problem Lecture 9: UCB Algorithm and Adversarial Bandit Problem EECS598: Prediction and Learning: It s Only a Game Fall 03 Lecture 9: UCB Algorithm and Adversarial Bandit Problem Prof. Jacob Abernethy Scribe:

More information

The Multi-Arm Bandit Framework

The Multi-Arm Bandit Framework The Multi-Arm Bandit Framework A. LAZARIC (SequeL Team @INRIA-Lille) ENS Cachan - Master 2 MVA SequeL INRIA Lille MVA-RL Course In This Lecture A. LAZARIC Reinforcement Learning Algorithms Oct 29th, 2013-2/94

More information

Evaluation of multi armed bandit algorithms and empirical algorithm

Evaluation of multi armed bandit algorithms and empirical algorithm Acta Technica 62, No. 2B/2017, 639 656 c 2017 Institute of Thermomechanics CAS, v.v.i. Evaluation of multi armed bandit algorithms and empirical algorithm Zhang Hong 2,3, Cao Xiushan 1, Pu Qiumei 1,4 Abstract.

More information

On the Complexity of Best Arm Identification in Multi-Armed Bandit Models

On the Complexity of Best Arm Identification in Multi-Armed Bandit Models On the Complexity of Best Arm Identification in Multi-Armed Bandit Models Aurélien Garivier Institut de Mathématiques de Toulouse Information Theory, Learning and Big Data Simons Institute, Berkeley, March

More information

Multi-Armed Bandits. Credit: David Silver. Google DeepMind. Presenter: Tianlu Wang

Multi-Armed Bandits. Credit: David Silver. Google DeepMind. Presenter: Tianlu Wang Multi-Armed Bandits Credit: David Silver Google DeepMind Presenter: Tianlu Wang Credit: David Silver (DeepMind) Multi-Armed Bandits Presenter: Tianlu Wang 1 / 27 Outline 1 Introduction Exploration vs.

More information

COS 402 Machine Learning and Artificial Intelligence Fall Lecture 22. Exploration & Exploitation in Reinforcement Learning: MAB, UCB, Exp3

COS 402 Machine Learning and Artificial Intelligence Fall Lecture 22. Exploration & Exploitation in Reinforcement Learning: MAB, UCB, Exp3 COS 402 Machine Learning and Artificial Intelligence Fall 2016 Lecture 22 Exploration & Exploitation in Reinforcement Learning: MAB, UCB, Exp3 How to balance exploration and exploitation in reinforcement

More information

Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems, Part I. Sébastien Bubeck Theory Group

Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems, Part I. Sébastien Bubeck Theory Group Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems, Part I Sébastien Bubeck Theory Group i.i.d. multi-armed bandit, Robbins [1952] i.i.d. multi-armed bandit, Robbins [1952] Known

More information

Stat 260/CS Learning in Sequential Decision Problems. Peter Bartlett

Stat 260/CS Learning in Sequential Decision Problems. Peter Bartlett Stat 260/CS 294-102. Learning in Sequential Decision Problems. Peter Bartlett 1. Multi-armed bandit algorithms. Concentration inequalities. P(X ǫ) exp( ψ (ǫ))). Cumulant generating function bounds. Hoeffding

More information

Reinforcement Learning

Reinforcement Learning Reinforcement Learning Lecture 5: Bandit optimisation Alexandre Proutiere, Sadegh Talebi, Jungseul Ok KTH, The Royal Institute of Technology Objectives of this lecture Introduce bandit optimisation: the

More information

Csaba Szepesvári 1. University of Alberta. Machine Learning Summer School, Ile de Re, France, 2008

Csaba Szepesvári 1. University of Alberta. Machine Learning Summer School, Ile de Re, France, 2008 LEARNING THEORY OF OPTIMAL DECISION MAKING PART I: ON-LINE LEARNING IN STOCHASTIC ENVIRONMENTS Csaba Szepesvári 1 1 Department of Computing Science University of Alberta Machine Learning Summer School,

More information

Grundlagen der Künstlichen Intelligenz

Grundlagen der Künstlichen Intelligenz Grundlagen der Künstlichen Intelligenz Uncertainty & Probabilities & Bandits Daniel Hennes 16.11.2017 (WS 2017/18) University Stuttgart - IPVS - Machine Learning & Robotics 1 Today Uncertainty Probability

More information

Stratégies bayésiennes et fréquentistes dans un modèle de bandit

Stratégies bayésiennes et fréquentistes dans un modèle de bandit Stratégies bayésiennes et fréquentistes dans un modèle de bandit thèse effectuée à Telecom ParisTech, co-dirigée par Olivier Cappé, Aurélien Garivier et Rémi Munos Journées MAS, Grenoble, 30 août 2016

More information

Introducing strategic measure actions in multi-armed bandits

Introducing strategic measure actions in multi-armed bandits 213 IEEE 24th International Symposium on Personal, Indoor and Mobile Radio Communications: Workshop on Cognitive Radio Medium Access Control and Network Solutions Introducing strategic measure actions

More information

Two optimization problems in a stochastic bandit model

Two optimization problems in a stochastic bandit model Two optimization problems in a stochastic bandit model Emilie Kaufmann joint work with Olivier Cappé, Aurélien Garivier and Shivaram Kalyanakrishnan Journées MAS 204, Toulouse Outline From stochastic optimization

More information

Finite-time Analysis of the Multiarmed Bandit Problem*

Finite-time Analysis of the Multiarmed Bandit Problem* Machine Learning, 47, 35 56, 00 c 00 Kluwer Academic Publishers. Manufactured in The Netherlands. Finite-time Analysis of the Multiarmed Bandit Problem* PETER AUER University of Technology Graz, A-8010

More information

Alireza Shafaei. Machine Learning Reading Group The University of British Columbia Summer 2017

Alireza Shafaei. Machine Learning Reading Group The University of British Columbia Summer 2017 s s Machine Learning Reading Group The University of British Columbia Summer 2017 (OCO) Convex 1/29 Outline (OCO) Convex Stochastic Bernoulli s (OCO) Convex 2/29 At each iteration t, the player chooses

More information

Reinforcement Learning

Reinforcement Learning Reinforcement Learning Lecture 6: RL algorithms 2.0 Alexandre Proutiere, Sadegh Talebi, Jungseul Ok KTH, The Royal Institute of Technology Objectives of this lecture Present and analyse two online algorithms

More information

Exploration. 2015/10/12 John Schulman

Exploration. 2015/10/12 John Schulman Exploration 2015/10/12 John Schulman What is the exploration problem? Given a long-lived agent (or long-running learning algorithm), how to balance exploration and exploitation to maximize long-term rewards

More information

Stochastic Contextual Bandits with Known. Reward Functions

Stochastic Contextual Bandits with Known. Reward Functions Stochastic Contextual Bandits with nown 1 Reward Functions Pranav Sakulkar and Bhaskar rishnamachari Ming Hsieh Department of Electrical Engineering Viterbi School of Engineering University of Southern

More information

Bayesian and Frequentist Methods in Bandit Models

Bayesian and Frequentist Methods in Bandit Models Bayesian and Frequentist Methods in Bandit Models Emilie Kaufmann, Telecom ParisTech Bayes In Paris, ENSAE, October 24th, 2013 Emilie Kaufmann (Telecom ParisTech) Bayesian and Frequentist Bandits BIP,

More information

Analysis of Thompson Sampling for the multi-armed bandit problem

Analysis of Thompson Sampling for the multi-armed bandit problem Analysis of Thompson Sampling for the multi-armed bandit problem Shipra Agrawal Microsoft Research India shipra@microsoft.com avin Goyal Microsoft Research India navingo@microsoft.com Abstract We show

More information

Learning Algorithms for Minimizing Queue Length Regret

Learning Algorithms for Minimizing Queue Length Regret Learning Algorithms for Minimizing Queue Length Regret Thomas Stahlbuhk Massachusetts Institute of Technology Cambridge, MA Brooke Shrader MIT Lincoln Laboratory Lexington, MA Eytan Modiano Massachusetts

More information

Multi-armed Bandits in the Presence of Side Observations in Social Networks

Multi-armed Bandits in the Presence of Side Observations in Social Networks 52nd IEEE Conference on Decision and Control December 0-3, 203. Florence, Italy Multi-armed Bandits in the Presence of Side Observations in Social Networks Swapna Buccapatnam, Atilla Eryilmaz, and Ness

More information

Dynamic resource allocation: Bandit problems and extensions

Dynamic resource allocation: Bandit problems and extensions Dynamic resource allocation: Bandit problems and extensions Aurélien Garivier Institut de Mathématiques de Toulouse MAD Seminar, Université Toulouse 1 October 3rd, 2014 The Bandit Model Roadmap 1 The Bandit

More information

Stochastic bandits: Explore-First and UCB

Stochastic bandits: Explore-First and UCB CSE599s, Spring 2014, Online Learning Lecture 15-2/19/2014 Stochastic bandits: Explore-First and UCB Lecturer: Brendan McMahan or Ofer Dekel Scribe: Javad Hosseini In this lecture, we like to answer this

More information

On Bayesian bandit algorithms

On Bayesian bandit algorithms On Bayesian bandit algorithms Emilie Kaufmann joint work with Olivier Cappé, Aurélien Garivier, Nathaniel Korda and Rémi Munos July 1st, 2012 Emilie Kaufmann (Telecom ParisTech) On Bayesian bandit algorithms

More information

Exploration and exploitation of scratch games

Exploration and exploitation of scratch games Mach Learn (2013) 92:377 401 DOI 10.1007/s10994-013-5359-2 Exploration and exploitation of scratch games Raphaël Féraud Tanguy Urvoy Received: 10 January 2013 / Accepted: 12 April 2013 / Published online:

More information

Large-scale Information Processing, Summer Recommender Systems (part 2)

Large-scale Information Processing, Summer Recommender Systems (part 2) Large-scale Information Processing, Summer 2015 5 th Exercise Recommender Systems (part 2) Emmanouil Tzouridis tzouridis@kma.informatik.tu-darmstadt.de Knowledge Mining & Assessment SVM question When a

More information

Stat 260/CS Learning in Sequential Decision Problems. Peter Bartlett

Stat 260/CS Learning in Sequential Decision Problems. Peter Bartlett Stat 260/CS 294-102. Learning in Sequential Decision Problems. Peter Bartlett 1. Adversarial bandits Definition: sequential game. Lower bounds on regret from the stochastic case. Exp3: exponential weights

More information

Online Learning and Sequential Decision Making

Online Learning and Sequential Decision Making Online Learning and Sequential Decision Making Emilie Kaufmann CNRS & CRIStAL, Inria SequeL, emilie.kaufmann@univ-lille.fr Research School, ENS Lyon, Novembre 12-13th 2018 Emilie Kaufmann Sequential Decision

More information

1 MDP Value Iteration Algorithm

1 MDP Value Iteration Algorithm CS 0. - Active Learning Problem Set Handed out: 4 Jan 009 Due: 9 Jan 009 MDP Value Iteration Algorithm. Implement the value iteration algorithm given in the lecture. That is, solve Bellman s equation using

More information

Bandits for Online Optimization

Bandits for Online Optimization Bandits for Online Optimization Nicolò Cesa-Bianchi Università degli Studi di Milano N. Cesa-Bianchi (UNIMI) Bandits for Online Optimization 1 / 16 The multiarmed bandit problem... K slot machines Each

More information

Learning to play K-armed bandit problems

Learning to play K-armed bandit problems Learning to play K-armed bandit problems Francis Maes 1, Louis Wehenkel 1 and Damien Ernst 1 1 University of Liège Dept. of Electrical Engineering and Computer Science Institut Montefiore, B28, B-4000,

More information

Logarithmic Online Regret Bounds for Undiscounted Reinforcement Learning

Logarithmic Online Regret Bounds for Undiscounted Reinforcement Learning Logarithmic Online Regret Bounds for Undiscounted Reinforcement Learning Peter Auer Ronald Ortner University of Leoben, Franz-Josef-Strasse 18, 8700 Leoben, Austria auer,rortner}@unileoben.ac.at Abstract

More information

An Estimation Based Allocation Rule with Super-linear Regret and Finite Lock-on Time for Time-dependent Multi-armed Bandit Processes

An Estimation Based Allocation Rule with Super-linear Regret and Finite Lock-on Time for Time-dependent Multi-armed Bandit Processes An Estimation Based Allocation Rule with Super-linear Regret and Finite Lock-on Time for Time-dependent Multi-armed Bandit Processes Prokopis C. Prokopiou, Peter E. Caines, and Aditya Mahajan McGill University

More information

Revisiting the Exploration-Exploitation Tradeoff in Bandit Models

Revisiting the Exploration-Exploitation Tradeoff in Bandit Models Revisiting the Exploration-Exploitation Tradeoff in Bandit Models joint work with Aurélien Garivier (IMT, Toulouse) and Tor Lattimore (University of Alberta) Workshop on Optimization and Decision-Making

More information

Multi-Armed Bandit Formulations for Identification and Control

Multi-Armed Bandit Formulations for Identification and Control Multi-Armed Bandit Formulations for Identification and Control Cristian R. Rojas Joint work with Matías I. Müller and Alexandre Proutiere KTH Royal Institute of Technology, Sweden ERNSI, September 24-27,

More information

Online regret in reinforcement learning

Online regret in reinforcement learning University of Leoben, Austria Tübingen, 31 July 2007 Undiscounted online regret I am interested in the difference (in rewards during learning) between an optimal policy and a reinforcement learner: T T

More information

Chapter 2 Stochastic Multi-armed Bandit

Chapter 2 Stochastic Multi-armed Bandit Chapter 2 Stochastic Multi-armed Bandit Abstract In this chapter, we present the formulation, theoretical bound, and algorithms for the stochastic MAB problem. Several important variants of stochastic

More information

Administration. CSCI567 Machine Learning (Fall 2018) Outline. Outline. HW5 is available, due on 11/18. Practice final will also be available soon.

Administration. CSCI567 Machine Learning (Fall 2018) Outline. Outline. HW5 is available, due on 11/18. Practice final will also be available soon. Administration CSCI567 Machine Learning Fall 2018 Prof. Haipeng Luo U of Southern California Nov 7, 2018 HW5 is available, due on 11/18. Practice final will also be available soon. Remaining weeks: 11/14,

More information

Introduction to Reinforcement Learning Part 3: Exploration for decision making, Application to games, optimization, and planning

Introduction to Reinforcement Learning Part 3: Exploration for decision making, Application to games, optimization, and planning Introduction to Reinforcement Learning Part 3: Exploration for decision making, Application to games, optimization, and planning Rémi Munos SequeL project: Sequential Learning http://researchers.lille.inria.fr/

More information

Sparse Linear Contextual Bandits via Relevance Vector Machines

Sparse Linear Contextual Bandits via Relevance Vector Machines Sparse Linear Contextual Bandits via Relevance Vector Machines Davis Gilton and Rebecca Willett Electrical and Computer Engineering University of Wisconsin-Madison Madison, WI 53706 Email: gilton@wisc.edu,

More information

EASINESS IN BANDITS. Gergely Neu. Pompeu Fabra University

EASINESS IN BANDITS. Gergely Neu. Pompeu Fabra University EASINESS IN BANDITS Gergely Neu Pompeu Fabra University EASINESS IN BANDITS Gergely Neu Pompeu Fabra University THE BANDIT PROBLEM Play for T rounds attempting to maximize rewards THE BANDIT PROBLEM Play

More information

Anytime optimal algorithms in stochastic multi-armed bandits

Anytime optimal algorithms in stochastic multi-armed bandits Rémy Degenne LPMA, Université Paris Diderot Vianney Perchet CREST, ENSAE REMYDEGENNE@MATHUNIV-PARIS-DIDEROTFR VIANNEYPERCHET@NORMALESUPORG Abstract We introduce an anytime algorithm for stochastic multi-armed

More information

Analysis of Thompson Sampling for the multi-armed bandit problem

Analysis of Thompson Sampling for the multi-armed bandit problem Analysis of Thompson Sampling for the multi-armed bandit problem Shipra Agrawal Microsoft Research India shipra@microsoft.com Navin Goyal Microsoft Research India navingo@microsoft.com Abstract The multi-armed

More information

Bandit Algorithms. Tor Lattimore & Csaba Szepesvári

Bandit Algorithms. Tor Lattimore & Csaba Szepesvári Bandit Algorithms Tor Lattimore & Csaba Szepesvári Bandits Time 1 2 3 4 5 6 7 8 9 10 11 12 Left arm $1 $0 $1 $1 $0 Right arm $1 $0 Five rounds to go. Which arm would you play next? Overview What are bandits,

More information

Ordinal Optimization and Multi Armed Bandit Techniques

Ordinal Optimization and Multi Armed Bandit Techniques Ordinal Optimization and Multi Armed Bandit Techniques Sandeep Juneja. with Peter Glynn September 10, 2014 The ordinal optimization problem Determining the best of d alternative designs for a system, on

More information

Thompson Sampling for the MNL-Bandit

Thompson Sampling for the MNL-Bandit JMLR: Workshop and Conference Proceedings vol 65: 3, 207 30th Annual Conference on Learning Theory Thompson Sampling for the MNL-Bandit author names withheld Editor: Under Review for COLT 207 Abstract

More information

Bandit Algorithms for Pure Exploration: Best Arm Identification and Game Tree Search. Wouter M. Koolen

Bandit Algorithms for Pure Exploration: Best Arm Identification and Game Tree Search. Wouter M. Koolen Bandit Algorithms for Pure Exploration: Best Arm Identification and Game Tree Search Wouter M. Koolen Machine Learning and Statistics for Structures Friday 23 rd February, 2018 Outline 1 Intro 2 Model

More information

Lecture 4: Lower Bounds (ending); Thompson Sampling

Lecture 4: Lower Bounds (ending); Thompson Sampling CMSC 858G: Bandits, Experts and Games 09/12/16 Lecture 4: Lower Bounds (ending); Thompson Sampling Instructor: Alex Slivkins Scribed by: Guowei Sun,Cheng Jie 1 Lower bounds on regret (ending) Recap from

More information

Piecewise-stationary Bandit Problems with Side Observations

Piecewise-stationary Bandit Problems with Side Observations Jia Yuan Yu jia.yu@mcgill.ca Department Electrical and Computer Engineering, McGill University, Montréal, Québec, Canada. Shie Mannor shie.mannor@mcgill.ca; shie@ee.technion.ac.il Department Electrical

More information

Adaptive Learning with Unknown Information Flows

Adaptive Learning with Unknown Information Flows Adaptive Learning with Unknown Information Flows Yonatan Gur Stanford University Ahmadreza Momeni Stanford University June 8, 018 Abstract An agent facing sequential decisions that are characterized by

More information

Ordinal optimization - Empirical large deviations rate estimators, and multi-armed bandit methods

Ordinal optimization - Empirical large deviations rate estimators, and multi-armed bandit methods Ordinal optimization - Empirical large deviations rate estimators, and multi-armed bandit methods Sandeep Juneja Tata Institute of Fundamental Research Mumbai, India joint work with Peter Glynn Applied

More information

Regional Multi-Armed Bandits

Regional Multi-Armed Bandits School of Information Science and Technology University of Science and Technology of China {wzy43, zrd7}@mail.ustc.edu.cn, congshen@ustc.edu.cn Abstract We consider a variant of the classic multiarmed

More information

New Algorithms for Contextual Bandits

New Algorithms for Contextual Bandits New Algorithms for Contextual Bandits Lev Reyzin Georgia Institute of Technology Work done at Yahoo! 1 S A. Beygelzimer, J. Langford, L. Li, L. Reyzin, R.E. Schapire Contextual Bandit Algorithms with Supervised

More information

Informational Confidence Bounds for Self-Normalized Averages and Applications

Informational Confidence Bounds for Self-Normalized Averages and Applications Informational Confidence Bounds for Self-Normalized Averages and Applications Aurélien Garivier Institut de Mathématiques de Toulouse - Université Paul Sabatier Thursday, September 12th 2013 Context Tree

More information

The Epoch-Greedy Algorithm for Contextual Multi-armed Bandits John Langford and Tong Zhang

The Epoch-Greedy Algorithm for Contextual Multi-armed Bandits John Langford and Tong Zhang The Epoch-Greedy Algorithm for Contextual Multi-armed Bandits John Langford and Tong Zhang Presentation by Terry Lam 02/2011 Outline The Contextual Bandit Problem Prior Works The Epoch Greedy Algorithm

More information

Lecture 4 January 23

Lecture 4 January 23 STAT 263/363: Experimental Design Winter 2016/17 Lecture 4 January 23 Lecturer: Art B. Owen Scribe: Zachary del Rosario 4.1 Bandits Bandits are a form of online (adaptive) experiments; i.e. samples are

More information

CCN Interest Forwarding Strategy as Multi-Armed Bandit Model with Delays

CCN Interest Forwarding Strategy as Multi-Armed Bandit Model with Delays CCN Interest Forwarding Strategy as Multi-Armed Bandit Model with Delays Konstantin Avrachenkov INRIA Sophia Antipolis France Email: k.avrachenkov@sophia.inria.fr Peter Jacko BCAM Basque Center for Applied

More information

Two generic principles in modern bandits: the optimistic principle and Thompson sampling

Two generic principles in modern bandits: the optimistic principle and Thompson sampling Two generic principles in modern bandits: the optimistic principle and Thompson sampling Rémi Munos INRIA Lille, France CSML Lunch Seminars, September 12, 2014 Outline Two principles: The optimistic principle

More information

arxiv: v2 [cs.lg] 3 Nov 2012

arxiv: v2 [cs.lg] 3 Nov 2012 arxiv:1204.5721v2 [cs.lg] 3 Nov 2012 Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems Sébastien Bubeck 1 and Nicolò Cesa-Bianchi 2 1 Department of Operations Research and Financial

More information

PAC Subset Selection in Stochastic Multi-armed Bandits

PAC Subset Selection in Stochastic Multi-armed Bandits In Langford, Pineau, editors, Proceedings of the 9th International Conference on Machine Learning, pp 655--66, Omnipress, New York, NY, USA, 0 PAC Subset Selection in Stochastic Multi-armed Bandits Shivaram

More information

On the robustness of a one-period look-ahead policy in multi-armed bandit problems

On the robustness of a one-period look-ahead policy in multi-armed bandit problems Procedia Computer Science 00 (200) (202) 0 635 644 International Conference on Computational Science, ICCS 200 Procedia Computer Science www.elsevier.com/locate/procedia On the robustness of a one-period

More information

Basics of reinforcement learning

Basics of reinforcement learning Basics of reinforcement learning Lucian Buşoniu TMLSS, 20 July 2018 Main idea of reinforcement learning (RL) Learn a sequential decision policy to optimize the cumulative performance of an unknown system

More information

A. Notation. Attraction probability of item d. (d) Highest attraction probability, (1) A

A. Notation. Attraction probability of item d. (d) Highest attraction probability, (1) A A Notation Symbol Definition (d) Attraction probability of item d max Highest attraction probability, (1) A Binary attraction vector, where A(d) is the attraction indicator of item d P Distribution over

More information

ONLINE ADVERTISEMENTS AND MULTI-ARMED BANDITS CHONG JIANG DISSERTATION

ONLINE ADVERTISEMENTS AND MULTI-ARMED BANDITS CHONG JIANG DISSERTATION c 2015 Chong Jiang ONLINE ADVERTISEMENTS AND MULTI-ARMED BANDITS BY CHONG JIANG DISSERTATION Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Electrical and

More information

Best Arm Identification in Multi-Armed Bandits

Best Arm Identification in Multi-Armed Bandits Best Arm Identification in Multi-Armed Bandits Jean-Yves Audibert Imagine, Université Paris Est & Willow, CNRS/ENS/INRIA, Paris, France audibert@certisenpcfr Sébastien Bubeck, Rémi Munos SequeL Project,

More information

Reward Maximization Under Uncertainty: Leveraging Side-Observations on Networks

Reward Maximization Under Uncertainty: Leveraging Side-Observations on Networks Reward Maximization Under Uncertainty: Leveraging Side-Observations Reward Maximization Under Uncertainty: Leveraging Side-Observations on Networks Swapna Buccapatnam AT&T Labs Research, Middletown, NJ

More information

Contextual Combinatorial Bandit and its Application on Diversified Online Recommendation

Contextual Combinatorial Bandit and its Application on Diversified Online Recommendation Contextual Combinatorial Bandit and its Application on Diversified Online Recommendation Lijing Qin Shouyuan Chen Xiaoyan Zhu Abstract Recommender systems are faced with new challenges that are beyond

More information

From Bandits to Monte-Carlo Tree Search: The Optimistic Principle Applied to Optimization and Planning

From Bandits to Monte-Carlo Tree Search: The Optimistic Principle Applied to Optimization and Planning From Bandits to Monte-Carlo Tree Search: The Optimistic Principle Applied to Optimization and Planning Rémi Munos To cite this version: Rémi Munos. From Bandits to Monte-Carlo Tree Search: The Optimistic

More information

Reducing contextual bandits to supervised learning

Reducing contextual bandits to supervised learning Reducing contextual bandits to supervised learning Daniel Hsu Columbia University Based on joint work with A. Agarwal, S. Kale, J. Langford, L. Li, and R. Schapire 1 Learning to interact: example #1 Practicing

More information

Stat 260/CS Learning in Sequential Decision Problems.

Stat 260/CS Learning in Sequential Decision Problems. Stat 260/CS 294-102. Learning in Sequential Decision Problems. Peter Bartlett 1. Multi-armed bandit algorithms. Exponential families. Cumulant generating function. KL-divergence. KL-UCB for an exponential

More information

The information complexity of sequential resource allocation

The information complexity of sequential resource allocation The information complexity of sequential resource allocation Emilie Kaufmann, joint work with Olivier Cappé, Aurélien Garivier and Shivaram Kalyanakrishan SMILE Seminar, ENS, June 8th, 205 Sequential allocation

More information

Optimistic Bayesian Sampling in Contextual-Bandit Problems

Optimistic Bayesian Sampling in Contextual-Bandit Problems Journal of Machine Learning Research volume (2012) 2069-2106 Submitted 7/11; Revised 5/12; Published 6/12 Optimistic Bayesian Sampling in Contextual-Bandit Problems Benedict C. May School of Mathematics

More information

Grundlagen der Künstlichen Intelligenz

Grundlagen der Künstlichen Intelligenz Grundlagen der Künstlichen Intelligenz Reinforcement learning Daniel Hennes 4.12.2017 (WS 2017/18) University Stuttgart - IPVS - Machine Learning & Robotics 1 Today Reinforcement learning Model based and

More information

Full-information Online Learning

Full-information Online Learning Introduction Expert Advice OCO LM A DA NANJING UNIVERSITY Full-information Lijun Zhang Nanjing University, China June 2, 2017 Outline Introduction Expert Advice OCO 1 Introduction Definitions Regret 2

More information

arxiv: v1 [cs.lg] 12 Sep 2017

arxiv: v1 [cs.lg] 12 Sep 2017 Adaptive Exploration-Exploitation Tradeoff for Opportunistic Bandits Huasen Wu, Xueying Guo,, Xin Liu University of California, Davis, CA, USA huasenwu@gmail.com guoxueying@outlook.com xinliu@ucdavis.edu

More information

Adaptive Concentration Inequalities for Sequential Decision Problems

Adaptive Concentration Inequalities for Sequential Decision Problems Adaptive Concentration Inequalities for Sequential Decision Problems Shengjia Zhao Tsinghua University zhaosj12@stanford.edu Ashish Sabharwal Allen Institute for AI AshishS@allenai.org Enze Zhou Tsinghua

More information

Bandits and Exploration: How do we (optimally) gather information? Sham M. Kakade

Bandits and Exploration: How do we (optimally) gather information? Sham M. Kakade Bandits and Exploration: How do we (optimally) gather information? Sham M. Kakade Machine Learning for Big Data CSE547/STAT548 University of Washington S. M. Kakade (UW) Optimization for Big data 1 / 22

More information

arxiv: v1 [cs.lg] 7 Sep 2018

arxiv: v1 [cs.lg] 7 Sep 2018 Analysis of Thompson Sampling for Combinatorial Multi-armed Bandit with Probabilistically Triggered Arms Alihan Hüyük Bilkent University Cem Tekin Bilkent University arxiv:809.02707v [cs.lg] 7 Sep 208

More information

Learning Exploration/Exploitation Strategies for Single Trajectory Reinforcement Learning

Learning Exploration/Exploitation Strategies for Single Trajectory Reinforcement Learning JMLR: Workshop and Conference Proceedings vol:1 8, 2012 10th European Workshop on Reinforcement Learning Learning Exploration/Exploitation Strategies for Single Trajectory Reinforcement Learning Michael

More information

KULLBACK-LEIBLER UPPER CONFIDENCE BOUNDS FOR OPTIMAL SEQUENTIAL ALLOCATION

KULLBACK-LEIBLER UPPER CONFIDENCE BOUNDS FOR OPTIMAL SEQUENTIAL ALLOCATION Submitted to the Annals of Statistics arxiv: math.pr/0000000 KULLBACK-LEIBLER UPPER CONFIDENCE BOUNDS FOR OPTIMAL SEQUENTIAL ALLOCATION By Olivier Cappé 1, Aurélien Garivier 2, Odalric-Ambrym Maillard

More information

Online Learning of Rested and Restless Bandits

Online Learning of Rested and Restless Bandits Online Learning of Rested and Restless Bandits Cem Tekin, Mingyan Liu Department of Electrical Engineering and Computer Science University of Michigan, Ann Arbor, Michigan, 48109-2122 Email: {cmtkn, mingyan}@umich.edu

More information

Exploiting Correlation in Finite-Armed Structured Bandits

Exploiting Correlation in Finite-Armed Structured Bandits Exploiting Correlation in Finite-Armed Structured Bandits Samarth Gupta Carnegie Mellon University Pittsburgh, PA 1513 Gauri Joshi Carnegie Mellon University Pittsburgh, PA 1513 Osman Yağan Carnegie Mellon

More information

THE first formalization of the multi-armed bandit problem

THE first formalization of the multi-armed bandit problem EDIC RESEARCH PROPOSAL 1 Multi-armed Bandits in a Network Farnood Salehi I&C, EPFL Abstract The multi-armed bandit problem is a sequential decision problem in which we have several options (arms). We can

More information

Multi-armed bandit based policies for cognitive radio s decision making issues

Multi-armed bandit based policies for cognitive radio s decision making issues Multi-armed bandit based policies for cognitive radio s decision making issues Wassim Jouini SUPELEC/IETR wassim.jouini@supelec.fr Damien Ernst University of Liège dernst@ulg.ac.be Christophe Moy SUPELEC/IETR

More information

Mechanisms with Learning for Stochastic Multi-armed Bandit Problems

Mechanisms with Learning for Stochastic Multi-armed Bandit Problems Mechanisms with Learning for Stochastic Multi-armed Bandit Problems Shweta Jain 1, Satyanath Bhat 1, Ganesh Ghalme 1, Divya Padmanabhan 1, and Y. Narahari 1 Department of Computer Science and Automation,

More information

Tsinghua Machine Learning Guest Lecture, June 9,

Tsinghua Machine Learning Guest Lecture, June 9, Tsinghua Machine Learning Guest Lecture, June 9, 2015 1 Lecture Outline Introduction: motivations and definitions for online learning Multi-armed bandit: canonical example of online learning Combinatorial

More information

Computational Oracle Inequalities for Large Scale Model Selection Problems

Computational Oracle Inequalities for Large Scale Model Selection Problems for Large Scale Model Selection Problems University of California at Berkeley Queensland University of Technology ETH Zürich, September 2011 Joint work with Alekh Agarwal, John Duchi and Clément Levrard.

More information

Stat 260/CS Learning in Sequential Decision Problems. Peter Bartlett

Stat 260/CS Learning in Sequential Decision Problems. Peter Bartlett Stat 260/CS 294-102. Learning in Sequential Decision Problems. Peter Bartlett 1. Thompson sampling Bernoulli strategy Regret bounds Extensions the flexibility of Bayesian strategies 1 Bayesian bandit strategies

More information

Profile-Based Bandit with Unknown Profiles

Profile-Based Bandit with Unknown Profiles Journal of Machine Learning Research 9 (208) -40 Submitted /7; Revised 6/8; Published 9/8 Profile-Based Bandit with Unknown Profiles Sylvain Lamprier sylvain.lamprier@lip6.fr Sorbonne Universités, UPMC

More information

Combinatorial Multi-Armed Bandit: General Framework, Results and Applications

Combinatorial Multi-Armed Bandit: General Framework, Results and Applications Combinatorial Multi-Armed Bandit: General Framework, Results and Applications Wei Chen Microsoft Research Asia, Beijing, China Yajun Wang Microsoft Research Asia, Beijing, China Yang Yuan Computer Science

More information

Multi-armed Bandit Algorithms and Empirical Evaluation

Multi-armed Bandit Algorithms and Empirical Evaluation Multi-armed Bandit Algorithms and Empirical Evaluation Joannès Vermorel 1 and Mehryar Mohri 2 1 École normale supérieure, 45 rue d Ulm, 75005 Paris, France joannes.vermorel@ens.fr 2 Courant Institute of

More information