Ting-Han Fan | DeepAI

AI Chat

Featured Co-authors

Hao Su
119 publications
Peter J. Ramadge
21 publications
Ta-Chung Chi
17 publications
Xian Yeow Lee
10 publications
Yubo Wang
10 publications
Alexander I. Rudnicky
9 publications
Yueh-Hua Wu
7 publications

∙ 09/14/2023

Advancing Regular Language Reasoning in Linear Recurrent Neural Networks

In recent studies, linear recurrent neural networks (LRNNs) have achieve...

0 Ting-Han Fan, et al. ∙

∙ 05/05/2023

Transformer Working Memory Enables Regular Language Reasoning and Natural Language Length Extrapolation

Unlike recurrent models, conventional wisdom has it that Transformers ca...

0 Ta-Chung Chi, et al. ∙

∙ 12/20/2022

Receptive Field Alignment Enables Transformer Length Extrapolation

Length extrapolation is a desirable property that permits training a tra...

0 Ta-Chung Chi, et al. ∙

∙ 06/15/2022

Training Discrete Deep Generative Models via Gapped Straight-Through Estimator

While deep generative models have succeeded in image processing, natural...

0 Ting-Han Fan, et al. ∙

∙ 05/20/2022

KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation

Relative positional embeddings (RPE) have received considerable attentio...

0 Ta-Chung Chi, et al. ∙

∙ 10/06/2021

Explaining Off-Policy Actor-Critic From A Bias-Variance Perspective

Off-policy Actor-Critic algorithms have demonstrated phenomenal experime...

0 Ting-Han Fan, et al. ∙

∙ 09/17/2021

Soft Actor-Critic With Integer Actions

Reinforcement learning is well-studied under discrete actions. Integer a...

0 Ting-Han Fan, et al. ∙

∙ 09/08/2021

PowerGym: A Reinforcement Learning Environment for Volt-Var Control in Power Distribution Systems

We introduce PowerGym, an open-source reinforcement learning environment...

0 Ting-Han Fan, et al. ∙

∙ 09/18/2020

A Contraction Approach to Model-based Reinforcement Learning

Model-based Reinforcement Learning has shown considerable experimental s...

0 Ting-Han Fan, et al. ∙

∙ 09/25/2019

Model Imitation for Model-Based Reinforcement Learning

Model-based reinforcement learning (MBRL) aims to learn a dynamic model ...

10 Yueh-Hua Wu, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world