activity
20102024
most citedApprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods

157 citations · 352 across the 23 of their papers we have counts for

collaborators
Showing cs.LGShow all

16 papers · 1 filter

cs.LG20243 cited

To Believe or Not to Believe Your LLM

Yasin Abbasi Yadkori, Ilja Kuzborskij, András György +1

We explore uncertainty quantification in large language models (LLMs), with the goal to identify when uncertainty in responses given a query is large. We simultaneously consider bo…

cs.LG20242 cited

Mitigating LLM Hallucinations via Conformal Abstention

Yasin Abbasi Yadkori, Ilja Kuzborskij, David Stutz +9

We develop a principled procedure for determining when a large language model (LLM) should abstain from responding (e.g., by saying "I don't know") in a general domain, instead of…

cs.LG2024

Regret Minimization via Saddle Point Optimization

Johannes Kirschner, Seyed Alireza Bakhtiari, Kushagra Chandak +2

A long line of works characterizes the sample complexity of regret minimization in sequential decision-making by min-max programs. In the corresponding saddle-point game, the min-p…

cs.LG2024

Stochastic Gradient Succeeds for Bandits

Jincheng Mei, Zixin Zhong, Bo Dai +3

We show that the \emph{stochastic gradient} bandit algorithm converges to a \emph{globally optimal} policy at an rate, even with a \emph{constant} step size. Remarkably, g…

cs.LG2023

Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice

Toshinori Kitamura, Tadashi Kozuno, Yunhao Tang +12

Mirror descent value iteration (MDVI), an abstraction of Kullback-Leibler (KL) and entropy-regularized reinforcement learning (RL), has served as the basis for recent high-performi…

cs.LG20231 cited

Exponential Hardness of Reinforcement Learning with Linear Function Approximation

Daniel Kane, Sihan Liu, Shachar Lovett +3

A fundamental question in reinforcement learning theory is: suppose the optimal value functions are linear in given features, can we learn them efficiently? This problem's counterp…