Login / Signup
Wesley Cowan
Publication Activity (10 Years)
Years Active: 2015-2023
Publications (10 Years): 7
Top Topics
Allocation Policies
Regret Bounds
Markov Decision Process
Reinforcement Learning
Top Venues
CoRR
J. Mach. Learn. Res.
</>
Publications
</>
Wesley Cowan
,
Michael N. Katehakis
,
Sheldon M. Ross
Optimal Activation of Halting Multi-Armed Bandit Models.
CoRR
(2023)
Wesley Cowan
,
Michael N. Katehakis
,
Daniel Pirutinsky
Accelerating the Computation of UCB and Related Indices for Reinforcement Learning.
CoRR
(2019)
Wesley Cowan
,
Michael N. Katehakis
,
Daniel Pirutinsky
Reinforcement Learning: a Comparison of UCB Versus Alternative Adaptive Policies.
CoRR
(2019)
Wesley Cowan
,
Junya Honda
,
Michael N. Katehakis
Normal Bandits of Unknown Means and Variances.
J. Mach. Learn. Res.
18 (2017)
Wesley Cowan
,
Michael N. Katehakis
Normal Bandits of Unknown Means and Variances: Asymptotic Optimality, Finite Horizon Regret Bounds, and a Solution to an Open Problem.
CoRR
(2015)
Wesley Cowan
,
Michael N. Katehakis
An Asymptotically Optimal UCB Policy for Uniform Bandits of Unknown Support.
CoRR
(2015)
Wesley Cowan
,
Michael N. Katehakis
Asymptotic Behavior of Minimal-Exploration Allocation Policies: Almost Sure, Arbitrarily Slow Growing Regret.
CoRR
(2015)