Yasin Abbasi-Yadkori

is this you? claim profile

∙ 0 followers
Google ∙ adobe ∙ University of Alberta ∙ qut

Data Scientist at Adobe Research

Improved Regret Bound and Experience Replay in Regularized Policy Iteration

In this work, we study algorithms for learning in infinite-horizon undis...
02/25/2021 ∙ by Nevena Lazic, et al. ∙ 0 ∙ share

read it
Optimization Issues in KL-Constrained Approximate Policy Iteration

Many reinforcement learning algorithms can be seen as versions of approx...
02/11/2021 ∙ by Nevena Lazic, et al. ∙ 0 ∙ share

read it
On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function

We consider the problem of local planning in fixed-horizon Markov Decisi...
02/03/2021 ∙ by Gellért Weisz, et al. ∙ 0 ∙ share

read it
The Elliptical Potential Lemma Revisited

This note proposes a new proof and new perspectives on the so-called Ell...
10/20/2020 ∙ by Alexandra Carpentier, et al. ∙ 0 ∙ share

read it
Regret Balancing for Bandit and RL Model Selection

We consider model selection in stochastic bandit and reinforcement learn...
06/09/2020 ∙ by Yasin Abbasi-Yadkori, et al. ∙ 9 ∙ share

read it
Sample Efficient Graph-Based Optimization with Noisy Observations

We study sample complexity of optimizing "hill-climbing friendly" functi...
06/04/2020 ∙ by Tan Nguyen, et al. ∙ 10 ∙ share

read it
Model Selection in Contextual Stochastic Bandit Problems

We study model selection in stochastic bandit problems. Our approach rel...
03/03/2020 ∙ by Aldo Pacchiano, et al. ∙ 0 ∙ share

read it
Provably Efficient Adaptive Approximate Policy Iteration

Model-free reinforcement learning algorithms combined with value functio...
02/08/2020 ∙ by Botao Hao, et al. ∙ 15 ∙ share

read it
Exploration-Enhanced POLITEX

We study algorithms for average-cost reinforcement learning problems wit...
08/27/2019 ∙ by Yasin Abbasi-Yadkori, et al. ∙ 1 ∙ share

read it
Thompson Sampling and Approximate Inference

We study the effects of approximate inference on the performance of Thom...
08/14/2019 ∙ by My Phan, et al. ∙ 0 ∙ share

read it
Bootstrapping Upper Confidence Bound

Upper Confidence Bound (UCB) method is arguably the most celebrated one ...
06/12/2019 ∙ by Botao Hao, et al. ∙ 0 ∙ share

read it
Large-Scale Markov Decision Problems via the Linear Programming Dual

We consider the problem of controlling a fully specified Markov decision...
01/06/2019 ∙ by Yasin Abbasi-Yadkori, et al. ∙ 0 ∙ share

read it
New Insights into Bootstrapping for Bandits

We investigate the use of bootstrapping in the bandit setting. We first ...
05/24/2018 ∙ by Sharan Vaswani, et al. ∙ 0 ∙ share

read it
Sharp Convergence Rates for Langevin Dynamics in the Nonconvex Setting

We study the problem of sampling from a distribution where the negative ...
05/04/2018 ∙ by Xiang Cheng, et al. ∙ 0 ∙ share

read it
Offline Evaluation of Ranking Policies with Click Models

Many web systems rank and present a list of items to users, from recomme...
04/27/2018 ∙ by Shuai Li, et al. ∙ 0 ∙ share

read it
Regret Bounds for Model-Free Linear Quadratic Control

Model-free approaches for reinforcement learning (RL) and continuous con...
04/17/2018 ∙ by Yasin Abbasi-Yadkori, et al. ∙ 0 ∙ share

read it
Optimizing over a Restricted Policy Class in Markov Decision Processes

We address the problem of finding an optimal policy in a Markov decision...
02/26/2018 ∙ by Ershad Banijamali, et al. ∙ 0 ∙ share

read it
A Continuation Method for Discrete Optimization and its Application to Nearest Neighbor Classification

The continuation method is a popular approach in non-convex optimization...
02/10/2018 ∙ by Ali Shameli, et al. ∙ 0 ∙ share

read it
Stochastic Low-Rank Bandits

Many problems in computer vision and recommender systems involve low-ran...
12/13/2017 ∙ by Branislav Kveton, et al. ∙ 0 ∙ share

read it
Posterior Sampling for Large Scale Reinforcement Learning

Posterior sampling for reinforcement learning (PSRL) is a popular algori...
11/21/2017 ∙ by Georgios Theocharous, et al. ∙ 0 ∙ share

read it
Conservative Contextual Linear Bandits

Safety is a desirable property that can immensely increase the applicabi...
11/19/2016 ∙ by Abbas Kazerouni, et al. ∙ 0 ∙ share

read it
Hit-and-Run for Sampling and Planning in Non-Convex Spaces

We propose the Hit-and-Run algorithm for planning and sampling problems ...
10/19/2016 ∙ by Yasin Abbasi-Yadkori, et al. ∙ 0 ∙ share

read it
Online learning in MDPs with side information

We study online learning of finite Markov decision process (MDP) problem...
06/26/2014 ∙ by Yasin Abbasi-Yadkori, et al. ∙ 0 ∙ share

read it
Linear Programming for Large-Scale Markov Decision Problems

We consider the problem of controlling a Markov decision process (MDP) w...
02/27/2014 ∙ by Yasin Abbasi-Yadkori, et al. ∙ 0 ∙ share

read it
Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions

We study the problem of learning Markov decision processes with finite s...
03/12/2013 ∙ by Yasin Abbasi-Yadkori, et al. ∙ 0 ∙ share

read it
Improved Mean and Variance Approximations for Belief Net Responses via Network Doubling

A Bayesian belief network models a joint distribution with an directed a...
05/09/2012 ∙ by Peter Hooper, et al. ∙ 0 ∙ share

read it
Online Least Squares Estimation with Self-Normalized Processes: An Application to Bandit Problems

The analysis of online least squares estimation is at the heart of many ...
02/14/2011 ∙ by Yasin Abbasi-Yadkori, et al. ∙ 0 ∙ share

read it

Yasin Abbasi-Yadkori

Featured Co-authors

Michael I. Jordan

Xi Chen

Csaba Szepesvari

Shuai Li

Mohammad Ghavamzadeh

Peter L. Bartlett

Dale Schuurmans

Guang Cheng

Tor Lattimore

Nan Jiang

Mark Schmidt

Improved Regret Bound and Experience Replay in Regularized Policy Iteration

Optimization Issues in KL-Constrained Approximate Policy Iteration

On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function

The Elliptical Potential Lemma Revisited

Regret Balancing for Bandit and RL Model Selection

Sample Efficient Graph-Based Optimization with Noisy Observations

Model Selection in Contextual Stochastic Bandit Problems

Provably Efficient Adaptive Approximate Policy Iteration

Exploration-Enhanced POLITEX

Thompson Sampling and Approximate Inference

Bootstrapping Upper Confidence Bound

Large-Scale Markov Decision Problems via the Linear Programming Dual

New Insights into Bootstrapping for Bandits

Sharp Convergence Rates for Langevin Dynamics in the Nonconvex Setting

Offline Evaluation of Ranking Policies with Click Models

Regret Bounds for Model-Free Linear Quadratic Control

Optimizing over a Restricted Policy Class in Markov Decision Processes

A Continuation Method for Discrete Optimization and its Application to Nearest Neighbor Classification

Stochastic Low-Rank Bandits

Posterior Sampling for Large Scale Reinforcement Learning

Conservative Contextual Linear Bandits

Hit-and-Run for Sampling and Planning in Non-Convex Spaces

Online learning in MDPs with side information

Linear Programming for Large-Scale Markov Decision Problems

Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions

Improved Mean and Variance Approximations for Belief Net Responses via Network Doubling

Online Least Squares Estimation with Self-Normalized Processes: An Application to Bandit Problems