Results 11 to 20 of about 3,478,919 (201)
Introduction to multi-armed bandits [PDF]
Foundations and Trends® in Machine Learning, 2019 Multi-armed bandits is a rich, multi-disciplinary area that has been studied since 1933, with a surge of activity in the past 10-15 years.
Slivkins, Aleksandrs
core +4 more sources
Finding structure in multi-armed bandits [PDF]
Cognitive Psychology, 2020 How do humans search for rewards? This question is commonly studied using multi-armed bandit tasks, which require participants to trade off exploration and exploitation.
Franklin, N., Schulz, E., Gershman, S.
core +5 more sources
Multi-armed Bandits with Missing Outcome
CoRRWhile significant progress has been made in designing algorithms that minimize regret in online decision-making, real-world scenarios often introduce additional complexities, perhaps the most challenging of which is missing outcomes.
Mahrooghi, Ilia +3 more
core +4 more sources
CoRRWe introduce a novel multi-armed bandit framework, where each arm is associated with a fixed unknown credal set over the space of outcomes (which can be richer than just the reward).
Kosoy, Vanessa
core +4 more sources
A generalised gittins index for a class of multi-armed bandits with general resource requirements [PDF]
, 2009 We generalise classical multiarmed bandits to allow for the distribution of a (fixed amount of a) divisible resource among the constituent bandits at each decision point.
Minty, R J, Glazebrook, K D
core +5 more sources
Ballooning Multi-Armed Bandits [PDF]
International Joint Conference on Autonomous Agents and Multiagent Systems, 2020 We introduce ballooning multi-armed bandits (BL-MAB), a novel extension to the classical stochastic MAB model. In the BL-MAB model, the set of available arms grows (or balloons) over time. The regret in a BL-MAB setting is computed with respect to the best available arm at each time.
Ganesh Ghalme +4 more
openaire +4 more sources
Multi-Armed Bandits With Correlated Arms [PDF]
IEEE Transactions on Information Theory, 2021 We consider a multi-armed bandit framework where the rewards obtained by pulling different arms are correlated. We develop a unified approach to leverage these reward correlations and present fundamental generalizations of classic bandit algorithms to the correlated setting.
Samarth Gupta +3 more
openaire +4 more sources
Modelling Cournot Games as Multi-agent Multi-armed Bandits
Proceedings of the International Florida Artificial Intelligence Research Society Conference, 2022 We investigate the use of a multi-agent multi-armed bandit (MA-MAB) setting for modeling repeated Cournot oligopoly games, where the firms acting as agents choose from the set of arms representing production quantity (a discrete value).
Kshitija Taywade +3 more
doaj +1 more source
Proceedings of the AAAI Conference on Artificial Intelligence, 2021 Federated multi-armed bandits (FMAB) is a new bandit paradigm that parallels the federated learning (FL) framework in supervised learning. It is inspired by practical applications in cognitive radio and recommender systems, and enjoys features that are analogous to FL.
Chengshuai Shi, Cong Shen 0001
openaire +3 more sources
The multi-armed bandit, with constraints [PDF]
Annals of Operations Research, 2012 The colorfully-named and much-studied multi-armed bandit is the following Markov decision problem: At epochs 1, 2, ... , a decision maker observes the current state of each of several Markov chains with rewards (bandits) and plays one of them. The Markov chains that are not played remain in their current states.
Eric V. Denardo +2 more
openaire +4 more sources