HKUNLP/DiffuSearch
[ICLR 2025] Code for the paper "Implicit Search via Discrete Diffusion: A Study on Chess"
This project offers a new way to train AI to play chess by enabling it to 'think ahead' without using traditional explicit search methods. It takes recorded chess games as input and produces an AI that can predict optimal moves, aiming for better action accuracy and higher Elo ratings. It's for researchers and AI enthusiasts interested in advanced planning algorithms for games or strategic decision-making.
No commits in the last 6 months.
Use this if you are a researcher or AI enthusiast keen on exploring novel implicit search methods, particularly in the context of game AI and strategic planning, and want to experiment with a chess-playing agent.
Not ideal if you are looking for the absolute strongest chess engine currently available, as it is still weaker than top state-of-the-art programs.
Stars
37
Forks
2
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 03, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/HKUNLP/DiffuSearch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ZhengYinan-AIR/Diffusion-Planner
[ICLR 2025 Oral] The official implementation of "Diffusion-Based Planning for Autonomous Driving...
intuitive-robots/MoDE_Diffusion_Policy
[ICLR 25] Code for "Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers...
caio-freitas/GraphDiffusionImitate
Diffusion-based graph generative policies for imitation learning in robotics tasks 🧠🤖
LeCAR-Lab/model-based-diffusion
Official implementation for the paper "Model-based Diffusion for Trajectory Optimization"....
Weixy21/SafeDiffuser
Safe Planning with Diffusion Probabilistic Models