research
∙
05/24/2023
Ranking with Popularity Bias: User Welfare under Self-Amplification Dynamics
While popularity bias is recognized to play a role in recommmender (and ...
share
research
∙
02/04/2023
Reinforcement Learning with History-Dependent Dynamic Contexts
We introduce Dynamic Contextual Markov Decision Processes (DCMDPs), a no...
research
∙
05/30/2022
Reinforcement Learning with a Terminator
We present the problem of reinforcement learning with exogenous terminat...
research
∙
10/12/2021
Dare not to Ask: Problem-Dependent Guarantees for Budgeted Bandits
We consider a stochastic multi-armed bandit setting where feedback is li...
research
∙
02/28/2021
Ensemble Bootstrapping for Q-Learning
Q-learning (QL), a common reinforcement learning algorithm, suffers from...
research
∙
08/13/2020
Reinforcement Learning with Trajectory Feedback
The computational model of reinforcement learning is based upon the abil...
research
∙
08/10/2020
Lenient Regret for Multi-Armed Bandits
We consider the Multi-Armed Bandit (MAB) problem, where the agent sequen...
research
∙
02/13/2020
Tight Lower Bounds for Combinatorial Multi-Armed Bandits
The Combinatorial Multi-Armed Bandit problem is a sequential decision-ma...
research
∙
10/02/2019
Stabilizing Off-Policy Reinforcement Learning with Conservative Policy Gradients
In recent years, advances in deep learning have enabled the application ...
research
∙
05/27/2019
Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies
State-of-the-art efficient model-based Reinforcement Learning (RL) algor...
research
∙
05/08/2019
Batch-Size Independent Regret Bounds for the Combinatorial Multi-Armed Bandit Problem
We consider the combinatorial multi-armed bandit (CMAB) problem, where t...
research
∙
09/06/2018