Yasin Abbasi-Yadkori

22 papers · 2011–2023 · 7 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+8 more ↓

🗺️ Taxonomy Completionist (31) 🏃 Academic Marathon · Half 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird

🧭 Keyword Pioneer 🤝 Dynamic Duo (10) 🚀 Conference Pioneer 🔥 Unstoppable · Bronze ⚡ Prolific Year · Productive 💎 Century Club · Bronze 📈 Trend Setter 🗃️ Keyword Collector (100)

Venues

AISTATS (8) ICML (7) COLT (3) ALT (1) JMLR (1) NeurIPS (1) UAI (1)

Top co-authors

Csaba Szepesvári (10) Peter Bartlett (7) Nevena Lazic (7) Alan Malek (4) Dong Yin (3) Botao Hao (3) Mohammad Ghavamzadeh (2) Gellert Weisz (2) Anup Rao (2) Victor Gabillon (2)

Research topics

Machine Learning (18) Optimization & Theory (16) Learning Types (12) Mathematics & Optimization (11) Reinforcement Learning (11) Optimization (11) Methods (10) Artificial Intelligence (5) Applications (4) Core AI (4) Core Methods (2) Mathematics (2) Learning Paradigms (1)

Keywords

regret bound (10) markov decision process (7) policy iteration (5) multi-armed bandit (4) online learning (3) reinforcement learning (3) convex optimization (2) function approximation (2) stochastic bandit (2) confidence set (2) expert prediction (2) best arm identification (2) policy optimization (2) linear function approximation (2) policy learning (1) graph-based optimization (1) kl divergence (1) non-convex optimization (1) feature selection (1) optimal control (1)

Papers

A New Look at Dynamic Regret for Non-Stationary Stochastic Bandits JMLR 2023 Confident Least Square Value Iteration with Local Access to a Simulator AISTATS 2022 Efficient local planning with linear function approximation ALT 2022 Feature and Parameter Selection in Stochastic Linear Bandits ICML 2022 Adaptive Approximate Policy Iteration AISTATS 2021 Improved Regret Bound and Experience Replay in Regularized Policy Iteration ICML 2021 On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function COLT 2021 Model-Free Linear Quadratic Control via Reduction to Expert Prediction AISTATS 2019 On Densification for Minwise Hashing UAI 2019 Optimizing over a Restricted Policy Class in MDPs AISTATS 2019 POLITEX: Regret Bounds for Policy Iteration using Expert Prediction ICML 2019 Sample Efficient Graph-Based Optimization with Noisy Observations AISTATS 2019 Best of both worlds: Stochastic & adversarial best-arm identification COLT 2018 Hit-and-Run for Sampling and Planning in Non-Convex Spaces AISTATS 2017 A Fast and Reliable Policy Improvement Algorithm AISTATS 2016 Large-Scale Markov Decision Problems with KL Control Cost and its Application to Crowdsourcing ICML 2015 Linear Programming for Large-Scale Markov Decision Problems ICML 2014 Prediction with Limited Advice and Multiarmed Bandits with Paid Observations ICML 2014 Tracking Adversarial Targets ICML 2014 Online-to-Confidence-Set Conversions and Application to Sparse Stochastic Bandits AISTATS 2012 Improved Algorithms for Linear Stochastic Bandits NeurIPS 2011 Regret Bounds for the Adaptive Control of Linear Quadratic Systems COLT 2011