19 citations · 100 across the 32 of their papers we have counts for
7 papers · 1 filter
Scalable Multi-Task Inverse Reinforcement Learning
Allen Tran, Jia Wan, Nathan Kallus +1
By learning transferable rewards, inverse reinforcement learning (IRL) enables counterfactual evaluation of agents under modified environments. Such transfer places strict requirem…
Reward Transfer from Inverse Reinforcement Learning: A Coupled Minimax Approach
Guang-Yuan Hao, Lars van der Laan, Aurélien Bibaut +1
We study the transfer of rewards learned using inverse reinforcement learning from expert demonstrations in one environment to reinforcement learning in a new, different environmen…
Efficient Inference for Inverse Reinforcement Learning and Dynamic Discrete Choice Models
Lars van der Laan, Aurélien Bibaut, Nathan Kallus
In many sequential decision-making problems, researchers observe actions but not the rewards that drive behavior, yet still wish to evaluate and compare counterfactual policies. In…
Inverse Reinforcement Learning with Just Classification and a Few Regressions
Lars van der Laan, Nathan Kallus, Aurelien Bibaut
Inverse reinforcement learning (IRL) aims to infer rewards from observed behavior, but rewards are not identified from the policy alone: many reward--value pairs can rationalize th…
Rate-adaptive model selection over a collection of black-box contextual bandit algorithms
Aurélien F. Bibaut, Antoine Chambaz, Mark J. van der Laan
We consider the model selection task in the stochastic contextual bandit setting. Suppose we are given a collection of base contextual bandit algorithms. We provide a master algori…
Generalized Policy Elimination: an efficient algorithm for Nonparametric Contextual Bandits
Aurélien F. Bibaut, Antoine Chambaz, Mark J. van der Laan
We propose the Generalized Policy Elimination (GPE) algorithm, an oracle-efficient contextual bandit (CB) algorithm inspired by the Policy Elimination algorithm of \cite{dudik2011}…
More Efficient Off-Policy Evaluation through Regularized Targeted Learning
Aurélien F. Bibaut, Ivana Malenica, Nikos Vlassis +1
We study the problem of off-policy evaluation (OPE) in Reinforcement Learning (RL), where the aim is to estimate the performance of a new policy given historical data that may have…