research
∙
03/20/2023
Bridging Imitation and Online Reinforcement Learning: An Optimistic Tale
In this paper, we address the following problem: Given an offline demons...
share
research
∙
02/18/2023
Approximate Thompson Sampling via Epistemic Neural Networks
Thompson sampling (TS) is a popular heuristic for action selection, but ...
research
∙
02/07/2023
Leveraging Demonstrations to Improve Online Learning: Quality Matters
We investigate the extent to which offline demonstration data can improv...
research
∙
07/01/2022
Robustness of Epinets against Distributional Shifts
Recent work introduced the epinet as a new approach to uncertainty model...
research
∙
06/08/2022
Ensembles for Uncertainty Estimation: Benefits of Prior Functions and Bootstrapping
In machine learning, an agent needs to estimate uncertainty to efficient...
research
∙
03/02/2022
An Analysis of Ensemble Sampling
Ensemble sampling serves as a practical approximation to Thompson sampli...
research
∙
02/28/2022
Evaluating High-Order Predictive Distributions in Deep Learning
Most work on supervised learning research has focused on marginal predic...
research
∙
10/09/2021
Evaluating Predictive Distributions: Does Bayesian Deep Learning Work?
Posterior predictive distributions quantify uncertainties ignored by poi...
research
∙
07/20/2021
Evaluating Probabilistic Inference in Deep Learning: Beyond Marginal Predictions
A fundamental challenge for any intelligent system is prediction: given ...
research
∙
07/19/2021
Epistemic Neural Networks
We introduce the epistemic neural network (ENN) as an interface for unce...
research
∙
04/20/2021
Joint Online Learning and Decision-making via Dual Mirror Descent
We consider an online revenue maximization problem over a finite time ho...
research
∙
03/06/2021
Reinforcement Learning, Bit by Bit
Reinforcement learning agents have demonstrated remarkable achievements ...
research
∙
01/05/2021
On the Approximation Relationship between Optimizing Ratio of Submodular (RS) and Difference of Submodular (DS) Functions
We demonstrate that from an algorithm guaranteeing an approximation fact...
research
∙
12/03/2020
Neural Contextual Bandits with Deep Representation and Shallow Exploration
We study a general class of contextual bandits, where each context-actio...
research
∙
10/05/2020
A Benchmark and Baseline for Language-Driven Image Editing
Language-driven image editing can significantly save the laborious image...
research
∙
08/17/2020
On the Sample Complexity of Reinforcement Learning with Policy Space Generalization
We study the optimal sample complexity in large-scale Reinforcement Lear...
research
∙
07/31/2020
Low-rank Tensor Bandits
In recent years, multi-dimensional online decision making has been playi...
research
∙
07/13/2020
Structured Policy Iteration for Linear Quadratic Regulator
Linear quadratic regulator (LQR) is one of the most popular frameworks t...
research
∙
07/09/2020
Influence Diagram Bandits: Variational Thompson Sampling for Structured Bandit Problems
We propose a novel framework for structured bandits, which we call an in...
research
∙
06/12/2020
Hypermodels for Exploration
We study the use of hypermodels to represent epistemic uncertainty and g...
research
∙
05/04/2020
Improving Adversarial Text Generation by Modeling the Distant Future
Auto-regressive text generation models usually focus on local fluency, a...
research
∙
01/20/2020
Nested-Wasserstein Self-Imitation Learning for Sequence Generation
Reinforcement learning (RL) has been widely studied for improving sequen...
research
∙
06/12/2019
Bootstrapping Upper Confidence Bound
Upper Confidence Bound (UCB) method is arguably the most celebrated one ...
research
∙
04/20/2019
Waterfall Bandits: Learning to Sell Ads Online
A popular approach to selling online advertising is by a waterfall, wher...
research
∙
03/04/2019
Stochastic Online Learning with Probabilistic Graph Feedback
We consider a problem of stochastic online learning with general probabi...
research
∙
02/19/2019
Scalable Thompson Sampling via Optimal Transport
Thompson sampling (TS) is a class of algorithms for sequential decision-...
research
∙
11/13/2018
Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits
We propose a multi-armed bandit algorithm that explores based on randomi...
research
∙
11/01/2018
Online Diverse Learning to Rank from Partial-Click Feedback
Learning to rank is an important problem in machine learning and recomme...
research
∙
06/03/2018
Conservative Exploration using Interleaving
In many practical problems, a learning agent may want to learn the best ...
research
∙
05/24/2018
New Insights into Bootstrapping for Bandits
We investigate the use of bootstrapping in the bandit setting. We first ...
research
∙
04/27/2018
Offline Evaluation of Ranking Policies with Click Models
Many web systems rank and present a list of items to users, from recomme...
research
∙
12/13/2017
Stochastic Low-Rank Bandits
Many problems in computer vision and recommender systems involve low-ran...
research
∙
11/21/2017
Posterior Sampling for Large Scale Reinforcement Learning
Posterior sampling for reinforcement learning (PSRL) is a popular algori...
research
∙
09/21/2017
SpectralFPL: Online Spectral Learning for Single Topic Models
This paper studies how to efficiently learn an optimal latent variable m...
research
∙
03/22/2017
Deep Exploration via Randomized Value Functions
We study the use of randomized value functions to guide deep exploration...
research
∙
03/19/2017
Bernoulli Rank-1 Bandits for Click Feedback
The probability that a user will click a search result depends both on i...
research
∙
03/07/2017
Online Learning to Rank in Stochastic Click Models
Online learning to rank is a core problem in information retrieval and m...
research
∙
08/10/2016
Stochastic Rank-1 Bandits
We propose stochastic rank-1 bandits, a class of online learning problem...
research
∙
05/21/2016
Online Influence Maximization under Independent Cascade Model with Semi-Bandit Feedback
We study the stochastic online problem of learning to influence in a soc...
research
∙
03/17/2016
Cascading Bandits for Large-Scale Recommendation Problems
Most recommender systems recommend a list of items. The user examines th...
research
∙
02/09/2016
DCM Bandits: Learning to Rank with Multiple Clicks
A search engine recommends to the user a list of web pages. The user exa...
research
∙
02/10/2015
Cascading Bandits: Learning to Rank in the Cascade Model
A search engine usually outputs a list of K web pages. The user examines...
research
∙
11/13/2014
DUM: Diversity-Weighted Utility Maximization for Recommendations
The need for diversification of recommendation lists manifests in a numb...
research
∙
10/03/2014
Tight Regret Bounds for Stochastic Combinatorial Semi-Bandits
A stochastic combinatorial semi-bandit is an online learning problem whe...
research
∙
06/28/2014
Efficient Learning in Large-Scale Combinatorial Semi-Bandits
A stochastic combinatorial semi-bandit is an online learning problem whe...
research
∙
05/30/2014
Learning to Act Greedily: Polymatroid Semi-Bandits
Many important optimization problems, such as the minimum spanning tree ...
research
∙
03/20/2014
Matroid Bandits: Fast Combinatorial Optimization with Learning
A matroid is a notion of independence in combinatorial optimization whic...
research
∙
02/04/2014
Generalization and Exploration via Randomized Value Functions
We propose randomized least-squares value iteration (RLSVI) -- a new rei...
research
∙
01/08/2014
Optimal Demand Response Using Device Based Reinforcement Learning
Demand response (DR) for residential and small commercial buildings is e...
research
∙
07/18/2013