paper-with-me

홈 › Papers

Greedy Algorithm almost Dominates in Smoothed Contextual Bandits

2020-05-19 · Manish Raghavan, Aleksandrs Slivkins, Jennifer Wortman Vaughan, Zhiwei Steven Wu

Online learning algorithms, widely used to power search and content optimization on the web, must balance exploration and exploitation, potentially sacrificing the experience of current users in order to gain information that will lead to better decisions in the future. While necessary in the worst case, explicit exploration has a number of disadvantages compared to the greedy algorithm that always "exploits" by choosing an action that currently looks optimal. We ask under what conditions inherent diversity in the data makes explicit exploration unnecessary. We build on a recent line of work on the smoothed analysis of the greedy algorithm in the linear contextual bandits model. We improve on prior results to show that a greedy approach almost matches the best possible Bayesian regret rate of any other algorithm on the same problem instance whenever the diversity conditions hold, and that this regret is at most $\tilde O(T^{1/3})$.

📄 PDF Abstract BibTeX arXiv:2005.10624

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityMulti-Armed Bandits

Similar Papers 제목 키워드 기반

Structured Linear Contextual Bandits: A Sharp and Geometric Smoothed Analysis

2020-02-26 · ICML 2020 1 · Vidyashankar Sivakumar, Zhiwei Steven Wu, Arindam Banerjee

Bandit learning algorithms typically involve the balance of exploration and exploitation. However, in many practical applications, worst-case scenarios needing systematic exploration are seldom encountered. In this work,…

Multi-Armed Bandits

A Smoothed Analysis of the Greedy Algorithm for the Linear Contextual Bandit Problem

2018-01-10 · NeurIPS 2018 12 · Sampath Kannan, Jamie Morgenstern, Aaron Roth, Bo Waggoner 외

Bandit learning is characterized by the tension between long-term exploration and short-term exploitation. However, as has recently been noted, in settings in which the choices of the learning algorithm correspond to imp…

Fairness

The Externalities of Exploration and How Data Diversity Helps Exploitation

2018-06-01 · Manish Raghavan, Aleksandrs Slivkins, Jennifer Wortman Vaughan, Zhiwei Steven Wu

Online learning algorithms, widely used to power search and content optimization on the web, must balance exploration and exploitation, potentially sacrificing the experience of current users for information that will le…

DiversityMulti-Armed Bandits

Multi-Armed Bandits for Correlated Markovian Environments with Smoothed Reward Feedback

2018-03-11 · Tanner Fiez, Shreyas Sekar, Lillian J. Ratliff

We study a multi-armed bandit problem in a dynamic environment where arm rewards evolve in a correlated fashion according to a Markov chain. Different than much of the work on related problems, in our formulation a learn…

Multi-Armed BanditsQ-Learning

Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework

2026-05-11 · Phalguni Nanda, Zaiwei Chen arxiv

In this work, we show that natural policy gradient, a core algorithm in reinforcement learning, admits an exact formulation as a smoothed and averaged form of policy iteration. Specifically, we introduce doubly smoothed …

Reinforcement Learning