5 papers
Principled Fast and Meta Knowledge Learners for Continual Reinforcement Learning
Ke Sun, Hongming Zhang, Jun Jin +4
Inspired by the human learning and memory system, particularly the interplay between the hippocampus and cerebral cortex, this study proposes a dual-learner framework comprising a…
A Deep Bayesian Nonparametric Framework for Robust Mutual Information Estimation
Forough Fazeliasl, Michael Minyi Zhang, Bei Jiang +1
Mutual Information (MI) is a crucial measure for capturing dependencies between variables, but exact computation is challenging in high dimensions with intractable likelihoods, imp…
ARMA-Design: Optimal Treatment Allocation Strategies for A/B Testing in Partially Observable Time Series Experiments
Ke Sun, Linglong Kong, Hongtu Zhu +1
Online experiments %in which experimental units receive a sequence of treatments over time are frequently employed in many technological companies to evaluate the performance of a…
Distributional Reinforcement Learning with Regularized Wasserstein Loss
Ke Sun, Yingnan Zhao, Wulong Liu +2
The empirical success of distributional reinforcement learning (RL) highly relies on the choice of distribution divergence equipped with an appropriate distribution representation.…
Oblivious subspace embeddings for compressed Tucker decompositions
Matthew Pietrosanu, Bei Jiang, Linglong Kong
Emphasis in the tensor literature on random embeddings (tools for low-distortion dimension reduction) for the canonical polyadic (CP) tensor decomposition has left analogous result…