5 papers
Exact Unlearning in Reinforcement Learning
Thanh Nguyen-Tang, Raman Arora
We formulate the problem of \emph{exact unlearning} in reinforcement learning, where the goal is to design an efficient framework that enables the removal of any user's data upon d…
Minimax-Optimal Policy Regret in Partially Observable Markov Games
Raman Arora
We study sequential decision-making in partially observable environments against strategic, adaptive opponents, modeled as partially observable Markov games (POMGs). The central ch…
On The Statistical Complexity of Offline Decision-Making
Thanh Nguyen-Tang, Raman Arora
We study the statistical complexity of offline decision-making with function approximation, establishing (near) minimax-optimal rates for stochastic contextual bandits and Markov d…
Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms
Thanh Nguyen-Tang, Raman Arora
We study learning in a dynamically evolving environment modeled as a Markov game between a learner and a strategic opponent that can adapt to the learner's strategies. While most e…
Offline Multitask Representation Learning for Reinforcement Learning
Haque Ishfaq, Thanh Nguyen-Tang, Songtao Feng +4
We study offline multitask representation learning in reinforcement learning (RL), where a learner is provided with an offline dataset from different tasks that share a common repr…