purpleyoung Goto Github PK

icychesszero

**象棋alpha zero程序

interactive-multi-objective-reinforcement-learning

Multi-objective reinforcement learning deals with finding policies for tasks where there are multiple distinct criteria to optimize for. Since there may be trade-offs between the criteria, there does not necessarily exist a globally best policy; instead, the goal is to find Pareto optimal policies that are the best for certain preference functions. The Pareto Q-learning algorithm looks for all Pareto optimal policies at the same time. Introduced a variant of Pareto Q-learning that asks queries to a user, who is assumed to have an underlying preference function and also the scalarized Q-learning algorithm which reduces the dimensionality of multi-objective space by using scalarization function and ask user preferences by taking weights for scalarization. The goal is to find the optimal policy for that user’s preference function as quickly as possible. Used two benchmark problems i.e. Deep Sea Treasure and Resource Collection for experiments.

java_nd4j_example

Nd4j using java example

javatdx

通达信java客户端

jstarcraft-ai

目标是提供一个完整的Java机器学习(Machine Learning/ML)框架,作为人工智能在学术界与工业界的桥梁. 让相关领域的研发人员能够在各种软硬件环境/数据结构/算法/模型之间无缝切换. 涵盖了从数据处理到模型的训练与评估各个环节,支持硬件加速和并行计算,是最快最全的Java机器学习库.

jumpy

A Python interface for ND4J: A Numpy Array Wrapper for the JVM

knn-for-pattern-recognize-

KNN形态识别 股票形态识别（如W双底）用图像识别的方法准确率高但速度慢（因要画图），用K-近邻方法以数值型数据计算快准确率基本符合要求(查准率70%左右)，可用于对决策时间有要求的交易。 工作完成情况： 1、W双底识别模型查准确率约70% 2、模型文件上载到聚宽后可在回测中调用。

ktdx

Kotlin (Java) version of tdx client

learn_rust

learning_pytorch_with_sherlockliao

廖星宇《深度学习入门之PyTorch》代码实践

leela-zero

Go engine with no human-provided knowledge, modeled after the AlphaGo Zero paper.

madmario

Interactive tutorial to build a learning Mario, for first-time RL learners

madrl

Repo containing code for multi-agent deep reinforcement learning (MADRL).

mas_stock_prediction

Simple Reinforcement Learning, Deep Reinforcement Learning, Federated, Multi Agent stock prediction code for this Google stocks dataset: https://www.kaggle.com/thevirusx3/google-stock-market-data

meta-learning

mini-alphastar

A mini-scale reproduction code of the AlphaStar program. Note: the original AlphaStar is the AI proposed by DeepMind to play StarCraft II.

multiagentreinforcementlearningsafetystockoptimizationandreorderinginuncertainties

This model explains how to build Multi Agent Reinforcement Learning Safety Stock Optimization And Reordering In Uncertainties

nd4j

Fast, Scientific and Numerical Computing for the JVM (NDArrays)

neuron_poker

Texas holdem OpenAi gym poker environment with reinforcement learning based on keras-rl. Includes virtual rendering and montecarlo for equity calculation.

numpywdl

Implement Wide & Deep algorithm by using NumPy

optimizing_stock_trading_using_reinforcement_learning

phoenixgo

Go AI program which implements the AlphaGo Zero paper

practical_rl

A course in reinforcement learning in the wild

project-checkers-coltec

Project developed by Gabriel Siroco and Samuel Henrique in COLTEC - UFMG.

py-mt4

🎰 用Python来写MT4的自动化交易脚本

python

Demo and other Python3 code

python-binance

Binance Exchange API python implementation for automated trading

python-checkers

python-checkers-ai

A checkers AI using the minimax algorithm.

pytorch-a3c

Simple A3C implementation with pytorch + multiprocessing