Slight modification to one of the Facebook Salina examples, to test the A2C algorithm on financial series.

Overview

Facebook Salina - Gym_AnyTrading

Slight modification of Facebook Salina Reinforcement Learning - A2C GPU example for financial series.

The gym FOREX data are provided by gym_anytrading library GitHub Page

With respect to the traditional CartPole-V0 gym, the stock_func is designed to provide in input a FOREX trading gym:

def stock_func(max_episode_steps,seed=123, window_size=10, size_sample=100):
    df =  FOREX_EURUSD_1H_ASK.copy()
    start_index = window_size
    if size_sample < 0:              ### put size_sample=-1 to consider the whole dataset.
        end_index = len(df)
    else:
        end_index = size_sample
    env = TimeLimit(gym.make('forex-v0', df=df, window_size=window_size, frame_bound=(start_index, end_index)), max_episode_steps=max_episode_steps)
    env.seed(seed)
    return env

A double tensor with diff close and relative gains are given in the gen_state function. The latter transforms the 'env/obs' tensors collected from AutoResetGymAgent into suitable tensors for Policy/Critic agent neural networks.

def _gen_state(observation):
    index = torch.tensor([0])
    diff_close = torch.transpose(torch.index_select(observation[0], 1, index), 1, 0)
    index2 = torch.tensor([1])
    buy_sell = torch.transpose(torch.index_select(observation[0], 1, index2), 1, 0)
    observation = torch.squeeze(torch.stack([diff_close, buy_sell], dim=1))
    return  observation

I take no responsibility for the use of the code. It is a simple test of SALINA's potential for financial problems.

The software license remains the one indicated in the source code and respectively linked to the official Facebook SALINA repository GitHub Page

Francesco Bardozzo, PhD [email protected] - NeuroneLab - University of Salerno - Italy

Pravesh Kriplani, PhD [email protected] - NeuroneLab - University of Salerno - Italy

Owner
Francesco Bardozzo
Researcher, PhD. Artificial and computational intelligence.
Francesco Bardozzo
Supplementary Data for Evolving Reinforcement Learning Algorithms

evolvingrl Supplementary Data for Evolving Reinforcement Learning Algorithms This dataset contains 1000 loss graphs from two experiments: 500 unique g

John Co-Reyes 42 Sep 21, 2022
A priority of preferences for teacher assignment problem

Genetic-Algorithm-for-Assignment-Problem A priority of preferences for teacher assignment problem Keywords k-partition; clustering; education 4.0 Abst

hades 2 Oct 31, 2022
A* (with 2 heuristic functions), BFS , DFS and DFS iterativeA* (with 2 heuristic functions), BFS , DFS and DFS iterative

Descpritpion This project solves the Taquin game (jeu de taquin) problem using different algorithms : A* (with 2 heuristic functions), BFS , DFS and D

Ayari Ahmed 3 May 09, 2022
A pure Python implementation of a mixed effects random forest (MERF) algorithm

Mixed Effects Random Forest This repository contains a pure Python implementation of a mixed effects random forest (MERF) algorithm. It can be used, o

Manifold 199 Dec 06, 2022
A library for benchmarking, developing and deploying deep learning anomaly detection algorithms

A library for benchmarking, developing and deploying deep learning anomaly detection algorithms Key Features • Getting Started • Docs • License Introd

OpenVINO Toolkit 1.5k Jan 04, 2023
PathPlanning - Common used path planning algorithms with animations.

Overview This repository implements some common path planning algorithms used in robotics, including Search-based algorithms and Sampling-based algori

Huiming Zhou 5.1k Jan 08, 2023
Python based framework providing a simple and intuitive framework for algorithmic trading

Harvest is a Python based framework providing a simple and intuitive framework for algorithmic trading. Visit Harvest's website for details, tutorials

100 Jan 03, 2023
Solving a card game with three search algorithms: BFS, IDS, and A*

Search Algorithms Overview In this project, we want to solve a card game with three search algorithms. In this card game, we have to sort our cards by

Korosh 5 Aug 04, 2022
The test data, code and detailed description of the AW t-SNE algorithm

AW-t-SNE The test data, code and result of the AW t-SNE algorithm Structure of the folder Datasets: This folder contains two datasets, the MNIST datas

1 Mar 09, 2022
Multiple Imputation with Random Forests in Python

miceforest: Fast, Memory Efficient Imputation with lightgbm Fast, memory efficient Multiple Imputation by Chained Equations (MICE) with lightgbm. The

Samuel Wilson 202 Dec 31, 2022
Apriori - An algorithm for frequent item set mining and association rule learning over relational databases

Apriori Apriori is an algorithm for frequent item set mining and association rul

Mohammad Nazari 8 Jan 10, 2022
FPE - Format Preserving Encryption with FF3 in Python

ff3 - Format Preserving Encryption in Python An implementation of the NIST approved FF3 and FF3-1 Format Preserving Encryption (FPE) algorithms in Pyt

Privacy Logistics 42 Dec 16, 2022
iAWE is a wonderful dataset for those of us who work on Non-Intrusive Load Monitoring (NILM) algorithms.

iAWE is a wonderful dataset for those of us who work on Non-Intrusive Load Monitoring (NILM) algorithms. You can find its main page and description via this link. If you are familiar with NILM-TK API

Mozaffar Etezadifar 3 Mar 19, 2022
This is an implementation of the QuickHull algorithm in Python. I

QuickHull This is an implementation of the QuickHull algorithm in Python. It randomly generates a set of points and finds the convex hull of this set

Anant Joshi 4 Dec 04, 2022
A lightweight, pure-Python mobile robot simulator designed for experiments in Artificial Intelligence (AI) and Machine Learning, especially for Jupyter Notebooks

aitk.robots A lightweight Python robot simulator for JupyterLab, Notebooks, and other Python environments. Goals A lightweight mobile robotics simulat

3 Oct 22, 2021
Sign data using symmetric-key algorithm encryption.

Sign data using symmetric-key algorithm encryption. Validate signed data and identify possible validation errors. Uses sha-(1, 224, 256, 385 and 512)/hmac for signature encryption. Custom hash algori

Artur Barseghyan 39 Jun 10, 2022
A selection of a few algorithms used to sort or search an array

Sort and search algorithms This repository has some common search / sort algorithms written in python, I also included the pseudocode of each algorith

0 Apr 02, 2022
SortingAlgorithmVisualization - A place for me to learn about sorting algorithms

SortingAlgorithmVisualization A place for me to learn about sorting algorithms.

1 Jan 15, 2022
Exam Schedule Generator using Genetic Algorithm

Exam Schedule Generator using Genetic Algorithm Requirements Use any kind of crossover Choose any justifiable rate of mutation Use roulette wheel sele

Sana Khan 1 Jan 12, 2022
Given a list of tickers, this algorithm generates a recommended portfolio for high-risk investors.

RiskyPortfolioGenerator Given a list of tickers, this algorithm generates a recommended portfolio for high-risk investors. Working in a group, we crea

Victoria Zhao 2 Jan 13, 2022