Search Results for author: Lili Wu

Found 8 papers, 2 papers with code

Rich-Observation Reinforcement Learning with Continuous Latent Dynamics

no code implementations29 May 2024 Yuda Song, Lili Wu, Dylan J. Foster, Akshay Krishnamurthy

The core of our algorithm is a new representation learning objective; we show that prior representation learning schemes tailored to discrete dynamics do not naturally extend to the continuous setting.

reinforcement-learning Representation Learning

Generalizing Multi-Step Inverse Models for Representation Learning to Finite-Memory POMDPs

no code implementations22 Apr 2024 Lili Wu, Ben Evans, Riashat Islam, Raihan Seraj, Yonathan Efroni, Alex Lamb

In this work, we consider the problem of discovering the agent-centric state in the more challenging high-dimensional non-Markovian setting, when the state can be decoded from a sequence of past observations.

Representation Learning

Renal function changes in chronic hepatitis B patients

no code implementations4 Mar 2024 Jinhua Zhao, Lili Wu, Xiaoan Yang, Zhilaing Gao, Hong Deng

Patients were categorized into stage 1 or stage 2 based on a baseline eGFR of less than 90 ml/min/m^2 Results: 125 CHB patients were matched 1:1 in both the combined treatment and cured groups.

Anytime-valid off-policy inference for contextual bandits

1 code implementation19 Oct 2022 Ian Waudby-Smith, Lili Wu, Aaditya Ramdas, Nikos Karampatziakis, Paul Mineiro

Importantly, our methods can be employed while the original experiment is still running (that is, not necessarily post-hoc), when the logging policy may be itself changing (due to learning), and even if the context distributions are a highly dependent time-series (such as if they are drifting over time).

counterfactual Multi-Armed Bandits +3

Parameterized Exploration

no code implementations13 Jul 2019 Jesse Clifton, Lili Wu, Eric Laber

We introduce Parameterized Exploration (PE), a simple family of methods for model-based tuning of the exploration schedule in sequential decision problems.

Multi-Armed Bandits

Multivariate Density Estimation with Missing Data

1 code implementation14 Aug 2018 Zhen Li, Lili Wu, Weilian Zhou, Sujit Ghosh

Multivariate density estimation is a popular technique in statistics with wide applications including regression models allowing for heteroskedasticity in conditional variances.

Methodology

Cannot find the paper you are looking for? You can Submit a new open access paper.