Undiscounted bandit games

Undiscounted bandit games

Show other versions (1)

We analyze undiscounted continuous-time games of strategic experimentation with two-armed bandits. The risky arm generates payoffs according to a Le´vy process with an unknown average payoff per unit of time which nature draws from an arbitrary finite set. Observing all actions and realized...

Fuld beskrivelse

Bibliografiske detaljer
Main Authors:	Keller, G, Rady, S
Format:	Working paper
Udgivet:	University of Oxford 2019

Lignende værker

Undiscounted bandit games
af: Keller, G, et al.
Udgivet: (2020)

Strategic experimentation with Poisson bandits.
af: Keller, G, et al.
Udgivet: (2010)

Strategic Experimentation with Exponential Bandits.
af: Keller, G, et al.
Udgivet: (2005)

Strategic Experimentation with Exponential Bandits.
af: Cripps, M, et al.
Udgivet: (2003)

Strategic experimentation with exponential bandits
af: Keller, G, et al.
Udgivet: (2003)

Mathematical relationship between ultimate pit limits generated by discounted and undiscounted block value maximization in open pit mining
af: Meisam Saleki, et al.
Udgivet: (2019-05-01)

Addictive Games: Case Study on Multi-Armed Bandit Game
af: Xiaohan Kang, et al.
Udgivet: (2021-12-01)

StreamingBandit: Experimenting with Bandit Policies
af: Jules Kruijswijk, et al.
Udgivet: (2020-08-01)

Regret of Multi-Channel Bandit Game in Cognitive Radio Networks
af: Ma Jun, et al.
Udgivet: (2016-01-01)

Branching Bandits: A Sequential Search Process with Correlated Pay-Offs.
af: Keller, G, et al.
Udgivet: (2003)

Batched Bandit Problems
af: Perchet, Vianney, et al.
Udgivet: (2015)

Linearly parameterized bandits
af: Tsitsiklis, John N., et al.
Udgivet: (2012)

Copeland dueling bandits
af: Zoghi, M, et al.
Udgivet: (2015)

Matching with semi-bandits
af: Kasy, M, et al.
Udgivet: (2022)

Architects, Bandits and Knights
af: Konstantin Lidin
Udgivet: (2006-03-01)

A Review of Multi-Armed Bandit Algorithms in Player Modeling and Game Design
af: Zhan Xizhi
Udgivet: (2025-01-01)

Nash Equilibrium of Social-Learning Agents in a Restless Multiarmed Bandit Game
af: Kazuaki Nakayama, et al.
Udgivet: (2017-05-01)

Global and Local Convergence Analysis of a Bandit Learning Algorithm in Merely Coherent Games
af: Yuanhanqing Huang, et al.
Udgivet: (2023-01-01)

Decentralized cooperative stochastic bandits
af: Martínez-Rubio, D, et al.
Udgivet: (2019)

Contextual bandits with cross-learning
Udgivet: (2021)

Contextual bandits with cross-learning
af: Balseiro, Santiago, et al.
Udgivet: (2021)

ON ERGODIC TWO-ARMED BANDITS
af: Tarres, P, et al.
Udgivet: (2012)

Behaviour and pupillometry in a bandit task
af: Moeller, M, et al.
Udgivet: (2021)

Multi-armed bandit approach for mean field game-based resource allocation in NOMA networks
af: Amani Benamor, et al.
Udgivet: (2024-05-01)

Nonstochastic Bandits with Infinitely Many Experts
af: Meng, X Flora, et al.
Udgivet: (2022)

The hungry bandit: The ballad of Yidak Kela
af: Jabb, L
Udgivet: (2014)

Bandit Problems under Censored Feedback
af: Guinet, Gauthier Marc Benoit
Udgivet: (2023)

Causally abstracted multi-armed bandits
af: Zennaro, FM, et al.
Udgivet: (2024)

Lantern Sam and the Blue Streak bandits /
af: Beil, Michael D author
Udgivet: (2014)

E. J. Hobsbawm, Les Bandits
af: Frank Noulin
Udgivet: (2009-07-01)

Signal detection models as contextual bandits
af: Thomas N. Sherratt, et al.
Udgivet: (2023-06-01)

A linear response bandit problem
af: Assaf Zeevi, et al.
Udgivet: (2013-01-01)

Conservative Contextual Combinatorial Cascading Bandit
af: Kun Wang
Udgivet: (2021-01-01)

When can the two-armed bandit algorithm be trusted?
af: Lamberton, D, et al.
Udgivet: (2004)

Multi-armed linear bandits with latent biases
af: Kang, Qiyu, et al.
Udgivet: (2024)

A hybrid bandit framework for diversified recommendation
af: Ding, Qinxu, et al.
Udgivet: (2021)

Thompson Sampling on Symmetric Alpha-Stable Bandits
af: Dubey, Abhimanyu, et al.
Udgivet: (2021)

Optimization as estimation with Gaussian processes in bandit settings
af: Wang, Zi, Ph.D. Massachusetts Institute of Technology
Udgivet: (2016)

Performance of bandit methods in acoustic relay positioning
af: Cheung, Mei Yi, et al.
Udgivet: (2015)

Thompson Sampling for Non-Stationary Bandit Problems
af: Han Qi, et al.
Udgivet: (2025-01-01)