24 citations · 69 across the 10 of their papers we have counts for
7 papers · 1 filter
Reachability-Aware Laplacian Representation in Reinforcement Learning
Kaixin Wang, Kuangqi Zhou, Jiashi Feng +2
In Reinforcement Learning (RL), Laplacian Representation (LapRep) is a task-agnostic state representation that encodes the geometry of the environment. A desirable property of LapR…
Online Learning for Non-monotone Submodular Maximization: From Full Information to Bandit Feedback
Qixin Zhang, Zengde Deng, Zaiyi Chen +3
In this paper, we revisit the online non-monotone continuous DR-submodular maximization problem over a down-closed convex set, which finds wide real-world applications in the domai…
Tyger: Task-Type-Generic Active Learning for Molecular Property Prediction
Kuangqi Zhou, Kaixin Wang, Jiashi Feng +3
How to accurately predict the properties of molecules is an essential problem in AI-driven drug discovery, which generally requires a large amount of annotation for training deep l…
The Geometry of Robust Value Functions
Kaixin Wang, Navdeep Kumar, Kuangqi Zhou +3
The space of value functions is a fundamental concept in reinforcement learning. Characterizing its geometric properties may provide insights for optimization and representation. E…
Value Penalized Q-Learning for Recommender Systems
Chengqian Gao, Ke Xu, Kuangqi Zhou +4
Scaling reinforcement learning (RL) to recommender systems (RS) is promising since maximizing the expected cumulative rewards for RL agents meets the objective of RS, i.e., improvi…
Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing
Kaixin Wang, Kuangqi Zhou, Qixin Zhang +3
The Laplacian representation recently gains increasing attention for reinforcement learning as it provides succinct and informative representation for states, by taking the eigenve…
Understanding and Resolving Performance Degradation in Graph Convolutional Networks
Kuangqi Zhou, Yanfei Dong, Kaixin Wang +4
A Graph Convolutional Network (GCN) stacks several layers and in each layer performs a PROPagation operation (PROP) and a TRANsformation operation (TRAN) for learning node represen…