FrostHan / vlog
varitional oracle guiding for reinforcement learning
☆11Updated 2 years ago
Alternatives and similar repositories for vlog:
Users that are interested in vlog are comparing it to the libraries listed below
- ☆20Updated 2 years ago
- 三人麻雀用AI☆15Updated last year
- Utility tools for tenhou.net log☆28Updated last year
- C++版日麻. Japanese Riichi Mahjong written in C++.☆104Updated 2 weeks ago
- 日本リーチ麻雀のゲームサーバー☆16Updated 2 years ago
- Deep reinforcement learning of mahjong self-play☆17Updated 6 years ago
- Mahjong game simulator for RiichiLab https://mjai.app☆64Updated this week
- Scripts for downloading logs from tenhou.net☆56Updated 8 years ago
- ☆9Updated 2 years ago
- Riichi Mahjong Kit: (1) Game log crawler (sqlite3, json, bs4); (2) Game log preprocessor; (3) Deterministic algorithms library☆51Updated 6 years ago
- User Interface of Mahjong AI☆15Updated 2 years ago
- golang package for working with tenhou net logs and protocol☆13Updated last year
- Game server for Japanese Mahjong AI.☆52Updated 3 years ago
- Tools to sniffer, decode, and archive API request and response from/to Mahjong Soul (雀魂) API☆40Updated 4 months ago
- ☆12Updated 3 years ago
- Mjx: A framework for Mahjong AI research☆174Updated 9 months ago
- 麻雀アルゴリズム☆14Updated 8 months ago
- Official Code Release for Pipeline PSRO: A Scalable Approach for Finding Approximate Nash Equilibria in Large Games☆47Updated 5 months ago
- Scripts to download phoenix logs from tenhou.net☆36Updated 7 months ago
- Python wrapper for the Mahjong Soul (Majsoul) Protobuf objects. It allows to use their API.☆74Updated 9 months ago
- A C++ library for the (self-proclaimed) world's fastest calculation of deficiency number (a.k.a. shanten number, 向聴数)☆10Updated last week
- Artificial Intelligence for Japanese mahjong☆245Updated 2 years ago
- An AI for 3-player Mahjong (Sanma) using deep reinforcement learning☆34Updated 6 months ago
- Deep RL Code for XDO: A Double Oracle Algorithm for Extensive-Form Games☆37Updated 3 years ago
- A tool for calculating the shanten number in Japanese mahjong.☆37Updated 2 weeks ago
- Code for "AutoCFR: Learning to Design Counterfatual Regret Minimization Algorithms", AAAI 2022 (Oral)☆16Updated 9 months ago
- An unoffical implementation of AlphaHoldem. 1v1 nl-holdem AI.☆77Updated last year
- ☆13Updated 3 years ago
- Deep reinforcement learning with tensorflow2☆92Updated 3 weeks ago
- ☆13Updated 2 years ago