activity
20202022
most citedEnsuring Monotonic Policy Improvement in Entropy-regularized Value-based Reinforcement Learning

4 citations · 4 across the 8 of their papers we have counts for

collaborators

8 papers

cs.LG2022

Enforcing KL Regularization in General Tsallis Entropy Reinforcement Learning via Advantage Learning

Lingwei Zhu, Zheng Chen, Eiji Uchibe +1

Maximum Tsallis entropy (MTE) framework in reinforcement learning has gained popularity recently by virtue of its flexible modeling choices including the widely used Shannon entrop…

cs.LG2022

-Munchausen Reinforcement Learning

Lingwei Zhu, Zheng Chen, Eiji Uchibe +1

The recently successful Munchausen Reinforcement Learning (M-RL) features implicit Kullback-Leibler (KL) regularization by augmenting the reward function with logarithm of the curr…

eess.SP2022

Multi-Tier Platform for Cognizing Massive Electroencephalogram

Zheng Chen, Lingwei Zhu, Ziwei Yang +1

An end-to-end platform assembling multiple tiers is built for precisely cognizing brain activities. Being fed massive electroencephalogram (EEG) data, the time-frequency spectrogra…

eess.SP2022

Adaptive Spike-Like Representation of EEG Signals for Sleep Stages Scoring

Lingwei Zhu, Koki Odani, Ziwei Yang +4

Recently there has seen promising results on automatic stage scoring by extracting spatio-temporal features from electroencephalogram (EEG). Such methods entail laborious manual fe…

cs.LG2022

Cancer Subtyping via Embedded Unsupervised Learning on Transcriptomics Data

Ziwei Yang, Lingwei Zhu, Zheng Chen +4

Cancer is one of the deadliest diseases worldwide. Accurate diagnosis and classification of cancer subtypes are indispensable for effective clinical treatment. Promising results on…

cs.LG2021

Geometric Value Iteration: Dynamic Error-Aware KL Regularization for Reinforcement Learning

Toshinori Kitamura, Lingwei Zhu, Takamitsu Matsubara

The recent boom in the literature on entropy-regularized reinforcement learning (RL) approaches reveals that Kullback-Leibler (KL) regularization brings advantages to RL algorithms…