Picture for Shin Ishii

Shin Ishii

Robust off-policy Reinforcement Learning via Soft Constrained Adversary

Add code
Aug 31, 2024
Viaarxiv icon

A Simple, Solid, and Reproducible Baseline for Bridge Bidding AI

Add code
Jun 14, 2024
Viaarxiv icon

A Batch Sequential Halving Algorithm without Performance Degradation

Add code
Jun 01, 2024
Viaarxiv icon

End-to-End Policy Gradient Method for POMDPs and Explainable Agents

Add code
Apr 19, 2023
Viaarxiv icon

Pgx: Hardware-accelerated parallel game simulation for reinforcement learning

Add code
Mar 29, 2023
Viaarxiv icon

EEGFuseNet: Hybrid Unsupervised Deep Feature Characterization and Fusion for High-Dimensional EEG with An Application to Emotion Recognition

Add code
Feb 07, 2021
Figure 1 for EEGFuseNet: Hybrid Unsupervised Deep Feature Characterization and Fusion for High-Dimensional EEG with An Application to Emotion Recognition
Figure 2 for EEGFuseNet: Hybrid Unsupervised Deep Feature Characterization and Fusion for High-Dimensional EEG with An Application to Emotion Recognition
Figure 3 for EEGFuseNet: Hybrid Unsupervised Deep Feature Characterization and Fusion for High-Dimensional EEG with An Application to Emotion Recognition
Figure 4 for EEGFuseNet: Hybrid Unsupervised Deep Feature Characterization and Fusion for High-Dimensional EEG with An Application to Emotion Recognition
Viaarxiv icon

MarmoNet: a pipeline for automated projection mapping of the common marmoset brain from whole-brain serial two-photon tomography

Add code
Aug 02, 2019
Figure 1 for MarmoNet: a pipeline for automated projection mapping of the common marmoset brain from whole-brain serial two-photon tomography
Figure 2 for MarmoNet: a pipeline for automated projection mapping of the common marmoset brain from whole-brain serial two-photon tomography
Figure 3 for MarmoNet: a pipeline for automated projection mapping of the common marmoset brain from whole-brain serial two-photon tomography
Figure 4 for MarmoNet: a pipeline for automated projection mapping of the common marmoset brain from whole-brain serial two-photon tomography
Viaarxiv icon

Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning

Add code
Jun 27, 2018
Figure 1 for Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
Figure 2 for Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
Figure 3 for Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
Figure 4 for Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
Viaarxiv icon

Efficient Diverse Ensemble for Discriminative Co-Tracking

Add code
Jun 07, 2018
Figure 1 for Efficient Diverse Ensemble for Discriminative Co-Tracking
Figure 2 for Efficient Diverse Ensemble for Discriminative Co-Tracking
Figure 3 for Efficient Diverse Ensemble for Discriminative Co-Tracking
Figure 4 for Efficient Diverse Ensemble for Discriminative Co-Tracking
Viaarxiv icon

Neural Sequence Model Training via $α$-divergence Minimization

Add code
Jun 30, 2017
Figure 1 for Neural Sequence Model Training via $α$-divergence Minimization
Figure 2 for Neural Sequence Model Training via $α$-divergence Minimization
Viaarxiv icon