Search Results for author:
Found 47 papers, 4 papers with code
Can large language models explore in-context?
We investigate the extent to which contemporary Large Language Models (LLMs) can engage in exploration, a core capability in reinforcement learning and decision making.
Impact of Decentralized Learning on Player Utilities in Stackelberg Games
To better understand such cases, we examine the learning dynamics of the two-agent system and the implications for each agent's objective.
Incentivized Exploration via Filtered Posterior Sampling
We study "incentivized exploration" (IE) in social learning problems where the principal (a recommendation algorithm) can leverage information asymmetry to incentivize sequentially-arriving agents to take exploratory actions.
Robust and Performance Incentivizing Algorithms for Multi-Armed Bandits with Strategic Agents
We identify a class of MAB algorithms which we call performance incentivizing which satisfy a collection of properties and show that they lead to mechanisms that incentivize top level performance at equilibrium and are robust under any strategy profile.
Algorithmic Persuasion Through Simulation
After a fixed number of queries, the sender commits to a messaging policy and the receiver takes the action that maximizes her expected utility given the message she receives.
Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Bandits
We consider offline policy optimization (OPO) in contextual bandits, where one is given a fixed dataset of logged interactions.
Bandit Social Learning: Exploration under Myopic Behavior
We study social learning dynamics motivated by reviews on online platforms.
Autobidders with Budget and ROI Constraints: Efficiency, Regret, and Pacing Dynamics
We study a game between autobidding algorithms that compete in an online advertising platform.
Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression
We consider contextual bandits with linear constraints (CBwLC), a variant of contextual bandits in which the algorithm consumes multiple resources subject to linear constraints on total consumption.
Incentivizing Combinatorial Bandit Exploration
The users are free to choose other actions and need to be incentivized to follow the algorithm's recommendations.
Content Filtering with Inattentive Information Consumers
We develop a model of content filtering as a game between the filter and the content consumer, where the latter incurs information costs for examining the content.
Bandits with Knapsacks beyond the Worst Case
Third, we provide a "generalreduction" from BwK to bandits which takes advantage of some known helpful structure, and apply this reduction to combinatorial semi-bandits, linear contextual bandits, and multinomial-logit bandits.
Sayer: Using Implicit Feedback to Optimize System Policies
We develop a methodology, called Sayer, that leverages implicit feedback to evaluate and train new system policies.
Exploration and Incentives in Reinforcement Learning
How do you incentivize self-interested agents to $\textit{explore}$ when they prefer to $\textit{exploit}$?
Competing Bandits: The Perils of Exploration Under Competition
Users arrive one by one and choose between the two firms, so that each firm makes progress on its bandit problem only if it is chosen.
Adaptive Discretization for Adversarial Lipschitz Bandits
We provide the first algorithm for adaptive discretization in the adversarial version, and derive instance-dependent regret bounds.
Efficient Contextual Bandits with Continuous Actions
We create a computationally tractable algorithm for contextual bandits with continuous actions having unknown structure.
Constrained episodic reinforcement learning in concave-convex and knapsack settings
We propose an algorithm for tabular episodic reinforcement learning with constraints.
Greedy Algorithm almost Dominates in Smoothed Contextual Bandits
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.
The Price of Incentivizing Exploration: A Characterization via Thompson Sampling and Sample Complexity
The performance loss due to incentives is therefore limited to the initial rounds when these data points are collected.
Bandits with Knapsacks beyond the Worst-Case
Third, we provide a general "reduction" from BwK to bandits which takes advantage of some known helpful structure, and apply this reduction to combinatorial semi-bandits, linear contextual bandits, and multinomial-logit bandits.
Corruption-robust exploration in episodic reinforcement learning
We initiate the study of multi-stage episodic reinforcement learning under adversarial corruptions in both the rewards and the transition probabilities of the underlying system extending recent results for the special case of stochastic bandits.
Introduction to Multi-Armed Bandits
This book provides a more introductory, textbook-like treatment of the subject.
Bayesian Exploration with Heterogeneous Agents
We consider Bayesian Exploration: a simple model in which the recommendation system (the "principal") controls the information flow to the users (the "agents") and strives to incentivize exploration via information asymmetry.
The Perils of Exploration under Competition: A Computational Modeling Approach
We empirically study the interplay between exploration and competition.
Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adapting
We study contextual bandit learning with an abstract policy class and continuous action space.
Adversarial Bandits with Knapsacks
We suggest a new algorithm for the stochastic version, which builds on the framework of regret minimization in repeated games and admits a substantially simpler analysis compared to prior work.
Incentivizing Exploration with Selective Data Disclosure
We propose and design recommendation systems that incentivize efficient exploration.
The Externalities of Exploration and How Data Diversity Helps Exploitation
Returning to group-level effects, we show that under the same conditions, negative group externalities essentially vanish under the greedy algorithm.
Combinatorial Semi-Bandits with Knapsacks
We unify two prominent lines of work on multi-armed bandits: bandits with knapsacks (BwK) and combinatorial semi-bandits.
Competing Bandits: Learning under Competition
Most modern systems strive to learn from interactions with users, and many engage in exploration: making potentially suboptimal choices for the sake of acquiring new information.
Multidimensional Dynamic Pricing for Welfare Maximization
We are able to apply this technique to the setting of unit demand buyers despite the fact that in that setting the goods are not divisible, and the natural fractional relaxation of a unit demand valuation is not strongly concave.
Bayesian Exploration: Incentivizing Exploration in Bayesian Games
As a key technical tool, we introduce the concept of explorable actions, the actions which some incentive-compatible policy can recommend with non-zero probability.
Contextual Dueling Bandits
The first of these algorithms achieves particularly low regret, even when data is adversarial, although its time and space requirements are linear in the size of the policy space.
How Many Workers to Ask? Adaptive Exploration for Collecting High Quality Labels
In this paper we investigate how to devise better stopping rules given such quality scores.
Adaptive Contract Design for Crowdsourcing Markets: Bandit Algorithms for Repeated Principal-Agent Problems
In this paper, we study the requester's problem of dynamically adjusting quality-contingent payments for tasks.
Resourceful Contextual Bandits
We study contextual bandits with ancillary constraints on resources, which are common in real-world applications such as choosing ads or dynamic pricing of items.
Bandits and Experts in Metric Spaces
In this work we study a very general setting for the multi-armed bandit problem in which the strategies form a metric space, and the payoff function satisfies a Lipschitz condition with respect to the metric.
Dynamic Ad Allocation: Bandits with Budgets
We consider an application of multi-armed bandits to internet advertising (specifically, to dynamic ad allocation in the pay-per-click model, with uncertainty on the click probabilities).
Bandits with Knapsacks
As one example of a concrete application, we consider the problem of dynamic posted pricing with limited supply and obtain the first algorithm whose regret, with respect to the optimal dynamic policy, is sublinear in the supply.
Adaptive Crowdsourcing Algorithms for the Bandit Survey Problem
This model is related to, but technically different from the well-known multi-armed bandit problem.
Multi-armed bandits on implicit metric spaces
For any given problem instance such a classification implicitly defines a similarity metric space, but the numerical similarity information is not available to the algorithm.
Dynamic Pricing with Limited Supply
The performance guarantee for the same mechanism can be improved to $O(\sqrt{k} \log n)$, with a distribution-dependent constant, if $k/n$ is sufficiently small.
Adapting to the Shifting Intent of Search Queries
Search engines today present results that are often oblivious to recent shifts in intent.
Contextual Bandits with Similarity Information
A particularly simple way to represent similarity information in the contextual bandit setting is via a "similarity distance" between the context-arm pairs which gives an upper bound on the difference between the respective expected payoffs.
Characterizing Truthful Multi-Armed Bandit Mechanisms
We investigate how the design of multi-armed bandit algorithms is affected by the restriction that the resulting mechanism must be truthful.
Multi-Armed Bandits in Metric Spaces
In this work we study a very general setting for the multi-armed bandit problem in which the strategies form a metric space, and the payoff function satisfies a Lipschitz condition with respect to the metric.
