X
Search Filters
Format Format
Format Format
X
Sort by Item Count (A-Z)
Filter by Count
Journal Article (1045) 1045
Conference Proceeding (441) 441
Publication (149) 149
Dissertation (70) 70
Book Chapter (45) 45
Newspaper Article (25) 25
Book / eBook (23) 23
Magazine Article (21) 21
Government Document (5) 5
Trade Publication Article (2) 2
Book Review (1) 1
Video Recording (1) 1
more...
Subjects Subjects
Subjects Subjects
X
Sort by Item Count (A-Z)
Filter by Count
algorithms (220) 220
optimization (202) 202
engineering, electrical & electronic (190) 190
multi-armed bandit (189) 189
multi-armed bandits (183) 183
online learning (145) 145
telecommunications (136) 136
computer science (135) 135
analysis (130) 130
operations research & management science (120) 120
machine learning (118) 118
statistics & probability (116) 116
markov processes (106) 106
dynamic programming (92) 92
studies (92) 92
computer science, artificial intelligence (91) 91
reinforcement learning (90) 90
indexes (87) 87
computer science, information systems (85) 85
bandits (84) 84
cognitive radio (83) 83
multiarmed bandit (83) 83
learning (82) 82
artificial intelligence (79) 79
gittins index (79) 79
bandit problem (74) 74
exploration (74) 74
policies (73) 73
bandit problems (72) 72
economics (72) 72
restless bandits (72) 72
multi-armed bandit problem (71) 71
scheduling (71) 71
decision making (67) 67
stochastic processes (67) 67
regret (66) 66
usage (64) 64
allocation (63) 63
computer science, theory & methods (63) 63
multiarmed bandit problem (63) 63
mathematics, applied (62) 62
sensors (62) 62
mathematical models (61) 61
random variables (61) 61
computer simulation (60) 60
games (60) 60
automation & control systems (58) 58
networks (58) 58
throughput (57) 57
mathematics (56) 56
wireless communication (53) 53
research (52) 52
statistics (52) 52
channels (48) 48
algorithm design and analysis (46) 46
bandit (46) 46
management (46) 46
recommender systems (45) 45
wireless networks (44) 44
computer science, hardware & architecture (43) 43
opportunistic spectrum access (43) 43
models (42) 42
uncertainty (42) 42
optimal policy (40) 40
contextual bandits (38) 38
multiarmed bandits (38) 38
online-lernen (38) 38
strategy (38) 38
computer science - learning (37) 37
resource management (36) 36
mathematical optimization (35) 35
methods (35) 35
optimality (35) 35
two-armed bandit (35) 35
interference (33) 33
mathematical analysis (33) 33
restless bandit (33) 33
model (32) 32
multi-armed bandit problems (32) 32
game theory (31) 31
upper bound (31) 31
convergence (30) 30
decision-making (30) 30
thompson sampling (30) 30
heuristic algorithms (29) 29
bayesian analysis (28) 28
context (28) 28
heuristics (28) 28
history (28) 28
resource allocation (28) 28
restless multi-armed bandit (28) 28
bands (27) 27
clinical trials (27) 27
experimentation (27) 27
index (27) 27
index medicus (27) 27
index policy (27) 27
markov decision process (27) 27
markov decision processes (27) 27
approximation (26) 26
more...
Library Location Library Location
Library Location Library Location
X
Sort by Item Count (A-Z)
Filter by Count
Robarts - Stacks (8) 8
Collection Dvlpm't (Acquisitions) - Vendor file (4) 4
Victoria University E.J. Pratt - Stacks (3) 3
Criminology - Stacks (2) 2
Mathematical Sciences - Stacks (2) 2
Pontifical Inst. Mediaeval Studies - Library use only (2) 2
UofT at Mississauga - Stacks (2) 2
UofT at Scarborough - Stacks (2) 2
Collection Dvlpm't (Acquisitions) - Closed Orders (1) 1
Engineering & Comp. Sci. - Stacks (1) 1
Innis College - Stacks (1) 1
Map & Data - Map Collection (1) 1
Media Commons - Audio Visual (1) 1
Media Commons - Library or classroom use (1) 1
OISE - Stacks (1) 1
Robarts - Not Returned (1) 1
St. Michael's College (John M. Kelly) - 2nd Floor (1) 1
Trinity College (John W Graham) - Stacks (1) 1
UTL at Downsview - May be requested (1) 1
more...
Language Language
Language Language
X
Sort by Item Count (A-Z)
Filter by Count
English (1489) 1489
French (73) 73
Chinese (9) 9
Japanese (9) 9
Spanish (6) 6
Korean (3) 3
Turkish (1) 1
more...
Publication Date Publication Date
Click on a bar to filter by decade
Slide to change publication date range


SIAM Journal on Computing, ISSN 0097-5397, 01/2003, Volume 32, Issue 1, pp. 48 - 77
In the multiarmed bandit problem, a gambler must decide which arm of K non-identical slot machines to play in a sequence of trials so as to maximize his... 
Adversarial bandit problem | Unknown matrix games | MATHEMATICS, APPLIED | COMPUTER SCIENCE, THEORY & METHODS | adversarial bandit problem | unknown matrix games
Journal Article
MACHINE LEARNING, ISSN 0885-6125, 02/2020, Volume 109, Issue 2, pp. 327 - 372
We study a bad arm existence checking problem in a stochastic K-armed bandit setting, in which a player's task is to judge whether a positive arm exists or all... 
Best arm identification | Online learning | Bandit problem | COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE | MULTIARMED BANDIT | Asymmetry | Algorithms
Journal Article
Journal of Computer and System Sciences, ISSN 0022-0000, 09/2012, Volume 78, Issue 5, pp. 1538 - 1556
We study a partial-information online-learning problem where actions are restricted to noisy comparisons between pairs of strategies (also known as bandits).... 
Multi-armed bandits | Preference elicitation | Online learning | COMPUTER SCIENCE, HARDWARE & ARCHITECTURE | COMPUTER SCIENCE, THEORY & METHODS | MULTIARMED BANDIT | Analysis | Algorithms | Food | Formulations | Retrieval | Feedback | Strategy | Taste | Foods | Optimization
Journal Article
The Annals of Statistics, ISSN 0090-5364, 4/2016, Volume 44, Issue 2, pp. 660 - 681
Motivated by practical applications, chiefly clinical trials, we study the regret achievable for stochastic bandits under the constraint that the employed... 
Grouped clinical trials, sample size determination, switching cost | Multi-armed bandit problems | Batches | Regret bounds | Multi-phase allocation | TESTS | grouped clinical trials | SELECTING 1 | switching cost | STATISTICS & PROBABILITY | MODEL | regret bounds | ALLOCATION | batches | multi-phase allocation | 2 ARMED BANDIT | sample size determination | 62L05 | 62C20
Journal Article
Machine Learning, ISSN 0885-6125, 5/2002, Volume 47, Issue 2, pp. 235 - 256
Reinforcement learning policies face the exploration versus exploitation dilemma, i.e. the search for a balance between exploring the environment to find... 
bandit problems | finite horizon regret | Automation and Robotics | Computer Science | Artificial Intelligence (incl. Robotics) | adaptive allocation rules | Computer Science, general | Adaptive allocation rules | Finite horizon regret | Bandit problems | POLICIES | COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE | Studies
Journal Article
Management Science, ISSN 0025-1909, 01/2016, Volume 62, Issue 1, pp. 264 - 285
The multiarmed bandit problem is a popular framework for studying the exploration versus exploitation trade-off. Recent applications include dynamic assortment... 
Robust control | Relative entropy | Model uncertainty | Games against nature | Bandit problems | model uncertainty | OPERATIONS RESEARCH & MANAGEMENT SCIENCE | bandit problems | MANAGEMENT | relative entropy | robust control | SYSTEMS | OPTIMIZATION | games against nature | MODEL | SELECTION | DYNAMIC ASSORTMENT | Algorithms | Research | Mathematical research | Game theory | Entropy (Information theory)
Journal Article
Neurocomputing, ISSN 0925-2312, 09/2016, Volume 205, pp. 16 - 21
We consider a variant of the multi-armed bandit model, which we call multi-armed bandit problem with known trend, where the gambler knows the shape of the... 
Online learning | Multi-armed bandit | Recommender systems | COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE | Analysis | Algorithms | Learning | Computer simulation | Confidence | Upper bounds | On-line systems | Trends | Standards
Journal Article
The Annals of Statistics, ISSN 0090-5364, 4/2013, Volume 41, Issue 2, pp. 693 - 721
Journal Article
Journal of Machine Learning Research, ISSN 1532-4435, 2012, Volume 23, p. 39.26
Journal Article
Neurocomputing, ISSN 0925-2312, 10/2018, Volume 310, pp. 201 - 212
In this paper, we propose a set of allocation strategies to deal with the multi-armed bandit problem, the possibilistic reward (PR) methods. First, we use... 
Multi-armed bandit problem | Possibilistic reward | Numerical study | REGRET BOUNDS | POLICIES | COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE | Analysis | Distribution (Probability theory) | Methods
Journal Article
Journal of Machine Learning Research, ISSN 1532-4435, 06/2012, Volume 13, pp. 2069 - 2106
Journal Article
IEEE Transactions on Neural Networks and Learning Systems, ISSN 2162-237X, 11/2018, Volume 29, Issue 11, pp. 5565 - 5580
Journal Article
ACM Transactions on Algorithms (TALG), ISSN 1549-6325, 10/2018, Volume 14, Issue 4, pp. 1 - 23
We introduce the dependent doors problem as an abstraction for situations in which one must perform a sequence of dependent decisions, without receiving... 
search | multi-armed bandit | no feedback | Combinatorics | Multi-armed bandit | No feedback | Search | MATHEMATICS, APPLIED | COMPUTER SCIENCE, THEORY & METHODS | Distributed, Parallel, and Cluster Computing | Computer Science
Journal Article
Journal of Machine Learning Research, ISSN 1532-4435, 2015, Volume 40, Issue 2015
Journal Article
IEEE Transactions on Automatic Control, ISSN 0018-9286, 08/2017, Volume 62, Issue 8, pp. 3788 - 3803
Satisficing is a relaxation of maximizing and allows for less risky decision making in the face of uncertainty. We propose two sets of satisficing objectives... 
Algorithm design and analysis | Context | Decision making | upper credible limit (UCL) | Linear programming | Robustness | Face | Standards | Multi-armed bandit | CHOICE | DECISION-MAKING | EXPLORATION | MODEL | AUTOMATION & CONTROL SYSTEMS | ENGINEERING, ELECTRICAL & ELECTRONIC | Usage | Algorithms | Research | Gaussian processes
Journal Article
IEEE/ACM Transactions on Networking, ISSN 1063-6692, 08/2016, Volume 24, Issue 4, pp. 2264 - 2277
Journal Article
Management Science, ISSN 0025-1909, 01/2020
Journal Article
Topics in Cognitive Science, ISSN 1756-8757, 04/2015, Volume 7, Issue 2, pp. 351 - 367
Journal Article
No results were found for your search.

Cannot display more than 1000 results, please narrow the terms of your search.