activity
20132026
most citedA Survey on Practical Applications of Multi-Armed and Contextual Bandits

107 citations · 165 across the 24 of their papers we have counts for

collaborators
Showing 2019Show all

7 papers · 1 filter

cs.AI20195 cited

How can AI Automate End-to-End Data Science?

Charu Aggarwal, Djallel Bouneffouf, Horst Samulowitz +9

Data science is labor-intensive and human experts are scarce but heavily involved in every aspect of it. This makes data science time consuming and restricted to experts with the r…

cs.AI201912 cited

A Bandit Approach to Posterior Dialog Orchestration Under a Budget

Sohini Upadhyay, Mayank Agarwal, Djallel Bounneffouf +1

Building multi-domain AI agents is a challenging task and an open problem in the area of AI. Within the domain of dialog, the ability to orchestrate multiple independently trained…

cs.LG2019

Split Q Learning: Reinforcement Learning with Two-Stream Rewards

Baihan Lin, Djallel Bouneffouf, Guillermo Cecchi

Drawing an inspiration from behavioral studies of human decision making, we propose here a general parametric framework for a reinforcement learning problem, which extends the stan…

cs.LG2019

A Story of Two Streams: Reinforcement Learning Models from Human Behavior and Neuropsychiatry

Baihan Lin, Guillermo Cecchi, Djallel Bouneffouf +2

Drawing an inspiration from behavioral studies of human decision making, we propose here a more general and flexible parametric framework for reinforcement learning that extends st…

cs.LG2019

Optimal Exploitation of Clustering and History Information in Multi-Armed Bandit

Djallel Bouneffouf, Srinivasan Parthasarathy, Horst Samulowitz +1

We consider the stochastic multi-armed bandit problem and the contextual bandit problem with historical observations and pre-clustered arms. The historical observations can contain…

cs.LG2019

An ADMM Based Framework for AutoML Pipeline Configuration

Sijia Liu, Parikshit Ram, Deepak Vijaykeerthy +6

We study the AutoML problem of automatically configuring machine learning pipelines by jointly selecting algorithms and their appropriate hyper-parameters for all steps in supervis…