rasca0027 / Mahjong4RLLinks
Mahjong4RL is a project that recreates the game of Japanese Mahjong and use deep reinforcement learning to play it.
☆12Updated 3 years ago
Alternatives and similar repositories for Mahjong4RL
Users that are interested in Mahjong4RL are comparing it to the libraries listed below
Sorting:
- Deep reinforcement learning of mahjong self-play☆17Updated 7 years ago
- varitional oracle guiding for reinforcement learning☆12Updated 3 years ago
- 基于GSConv+SlimNeck的YOLOv5的消防通道占用检测系统☆10Updated 2 years ago
- C++版日麻. Japanese Riichi Mahjong written in C++.☆120Updated 11 months ago
- 日本リーチ麻雀のゲームサーバー☆16Updated last month
- Exploring algorithms in the domain of offline reinforcement learning (REM, Ensemble-DQN, DQN, ...)☆16Updated 5 years ago
- golang package for working with tenhou net logs and protocol☆13Updated 6 months ago
- Riichi Mahjong Kit: (1) Game log crawler (sqlite3, json, bs4); (2) Game log preprocessor; (3) Deterministic algorithms library☆52Updated 7 years ago
- An AI for 3-player Mahjong (Sanma) using deep reinforcement learning☆42Updated last year
- A particle swarm optimizer using the GPU (PyTorch).☆21Updated 2 years ago
- 基于RLCard平台的麻将mahjong博弈游戏代码，包括基于规则和基于Dueling DQN的Agent模型。☆32Updated 3 years ago
- 三人麻雀用AI☆18Updated 2 years ago
- I have developed a custom environment using OpenAI Gym in Python for simulating a 5G wireless communication channel as part of a reinforc…☆13Updated last year
- Codification used for the AAMAS-17 paper "Simultaneously Learning and Advising in Multiagent Reinforcement Learning"☆15Updated 8 years ago
- Deep Reinforcement Learning by using Phasic Policy Gradient in Pytorch & Tensorflow☆20Updated 4 years ago
- Reinforcement learning (RL) implementation of imperfect information game Mahjong using markov decision processes to predict future game s…☆99Updated 3 years ago
- Using Reinforcement Learning method to realize load balancing control in dynamic cellular network☆11Updated 7 years ago
- Modified version of the LeagueSandbox project which relies on a Redis server to accept actions and send observations. Intended for reinfo…☆11Updated 9 months ago
- ☆24Updated 3 years ago
- 本文提出了一种基于多视图卷积神经网络的三维物体识别算法，以实现三维物体的准确识别。首先实现一个标准的卷积神经网络架构，该架构经过训练可以独立地识别形状的渲染视图，以实现即使从单一视图中也可以识别出一个三维形状。随后使用该三维物体多个角度的二维视图通过卷积神经网络识别的结果进…☆11Updated 3 years ago
- An implementation of main reinforcement learning algorithms: solo-agent and ensembled versions.☆13Updated 6 years ago
- Game server for Japanese Mahjong AI.☆59Updated 4 years ago
- Based on NS-3, design new GPSR routing protocols.☆13Updated 7 years ago
- 麻雀アルゴリズム☆16Updated last week
- PyTorch implementation of Vanilla PG, TNPG, TRPO, PPO on Mujoco environment☆12Updated 6 years ago
- Python wrapper for the Mahjong Soul (Majsoul) Protobuf objects. It allows to use their API.☆88Updated 2 months ago
- A RL benchmark framework based on real world problem☆13Updated 2 years ago
- Utility tools for tenhou.net log☆31Updated last year
- A Japanese Mahjong AI, which can play Mahjong on two online Japanese Mahjong services. It can easily defeat other players in 一般 (Normal l…☆150Updated 2 years ago
- Simple Wireless-Sensor-Network Optimization using Genetic-Algorithm.☆15Updated 10 months ago