Picture for Ti-Rong Wu

Ti-Rong Wu

Solving 7x7 Killall-Go with Seki Database

Add code
Nov 08, 2024
Viaarxiv icon

Interpreting the Learned Model in MuZero Planning

Add code
Nov 07, 2024
Viaarxiv icon

ResTNet: Defense against Adversarial Policies via Transformer in Computer Go

Add code
Oct 07, 2024
Viaarxiv icon

Game Solving with Online Fine-Tuning

Add code
Nov 13, 2023
Viaarxiv icon

MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games

Add code
Oct 17, 2023
Viaarxiv icon

A Local-Pattern Related Look-Up Table

Add code
Dec 22, 2022
Viaarxiv icon

Are AlphaZero-like Agents Robust to Adversarial Perturbations?

Add code
Nov 07, 2022
Viaarxiv icon

A Novel Approach to Solving Goal-Achieving Problems for Board Games

Add code
Dec 05, 2021
Figure 1 for A Novel Approach to Solving Goal-Achieving Problems for Board Games
Figure 2 for A Novel Approach to Solving Goal-Achieving Problems for Board Games
Figure 3 for A Novel Approach to Solving Goal-Achieving Problems for Board Games
Figure 4 for A Novel Approach to Solving Goal-Achieving Problems for Board Games
Viaarxiv icon

Learning to Stop: Dynamic Simulation Monte-Carlo Tree Search

Add code
Dec 14, 2020
Figure 1 for Learning to Stop: Dynamic Simulation Monte-Carlo Tree Search
Figure 2 for Learning to Stop: Dynamic Simulation Monte-Carlo Tree Search
Figure 3 for Learning to Stop: Dynamic Simulation Monte-Carlo Tree Search
Figure 4 for Learning to Stop: Dynamic Simulation Monte-Carlo Tree Search
Viaarxiv icon

Accelerating and Improving AlphaZero Using Population Based Training

Add code
Mar 13, 2020
Figure 1 for Accelerating and Improving AlphaZero Using Population Based Training
Figure 2 for Accelerating and Improving AlphaZero Using Population Based Training
Figure 3 for Accelerating and Improving AlphaZero Using Population Based Training
Figure 4 for Accelerating and Improving AlphaZero Using Population Based Training
Viaarxiv icon