RLStructures is a library to facilitate the implementation of new reinforcement learning algorithms.

Overview

TL;DR

TL;DR: RLStructures is a lightweight Python library that provides simple APIs as well as data structures that make as few assumptions as possible about the structure of your agent or your task, while allowing for transparently executing multiple policies on multiple environments in parallel (incl. multiple GPUs). It thus facilitates the implementation of RL algorithms while avoiding complex abstractions.

Why/What?

RL research addresses multiple aspects of RL like hierarchical policies, option-based policies, goal-oriented policies, structured input/output spaces, transformer-based policies, etc. while many available tools are specific to particular settings.

We propose RLStructures as a way to i) simulate multiple policies, multiple models and multiple environments simultaneously at scale ii) define complex loss functions and iii) quickly implement various policy architectures.

The main principle of RLStructures is to allow the user to delegate the sampling of trajectories and episodes to the library so they can spend most of their time on the interesting part of RL research: developing new models and algorithms.

RLStructures is easy to use: it has very few simple interfaces that can be learned in one hour by reading the tutorials. It is not a RL Alorithms catalog, but a library to do RL Research. For illustration purposes it comes with multiple RL algorithms including A2C, PPO, DDQN and SAC.

Installation

Install from source by running the following inside the repo:

pip install .

Learning RLStructures

The complete documentation is available at http://facebookresearch.github.io/rlstructures and tutorials can be found in the tutorial/ directory. The example algorithms are provided in raglos/.

A facebook group is also open for discussion.

List of Papers using rlstructures

Citing RLStructures

Please use this bibtex if you want to cite this repository in your publications:

    @misc{rlstructures,
        author = {L. Denoyer, D. Rothermel and X. Martinet},
        title = {{RLStructures - A simple library for RL research}},
        year = {2021},
        publisher = {GitHub},
        journal = {GitHub repository},
        howpublished = {\url{https://gitHub.com/facebookresearch/rlstructures}},
    }

  • Author: Ludovic Denoyer
  • Co-authors: Danielle Rothermel, Xavier Martinet
  • Other contributors: many....

License

rlstructures is released under the MIT license. See LICENSE for additional details about it. See also our Terms of Use and Privacy Policy.

Owner
Facebook Research
Facebook Research
My solutions to the competitive programming problems on LeetCode, USACO, LintCode, etc.

This repository holds my solutions to the competitive programming problems on LeetCode, USACO, LintCode, CCC, UVa, SPOJ, and Codeforces. The LeetCode

Yu Shen 32 Sep 17, 2022
A DSA repository but everything is in python.

DSA Status Contents A: Mathematics B: Bit Magic C: Recursion D: Arrays E: Searching F: Sorting G: Matrix H: Hashing I: String J: Linked List K: Stack

Shubhashish Dixit 63 Dec 23, 2022
Map single-cell transcriptomes to copy number evolutionary trees.

Map single-cell transcriptomes to copy number evolutionary trees. Check out the tutorial for more information. Installation $ pip install scatrex SCA

Computational Biology Group (CBG) 12 Jan 01, 2023
Array is a functional mutable sequence inheriting from Python's built-in list.

funct.Array Array is a functional mutable sequence inheriting from Python's built-in list. Array provides 100+ higher-order methods and more functiona

182 Nov 21, 2022
Chemical Structure Generator

CSG: Chemical Structure Generator A simple Chemical Structure Generator. Requirements Python 3 (= v3.8) PyQt5 (optional; = v5.15.0 required for grap

JP&K 5 Oct 22, 2022
Multidict is dict-like collection of key-value pairs where key might be occurred more than once in the container.

multidict Multidict is dict-like collection of key-value pairs where key might be occurred more than once in the container. Introduction HTTP Headers

aio-libs 325 Dec 27, 2022
Webtesting for course Data Structures & Algorithms

Selenium job to automate queries to check last posts of Module Data Structures & Algorithms Web-testing for course Data Structures & Algorithms Struct

1 Dec 15, 2021
One-Stop Destination for codes of all Data Structures & Algorithms

CodingSimplified_GK This repository is aimed at creating a One stop Destination of codes of all Data structures and Algorithms along with basic explai

Geetika Kaushik 21 Sep 26, 2022
A JSON-friendly data structure which allows both object attributes and dictionary keys and values to be used simultaneously and interchangeably.

A JSON-friendly data structure which allows both object attributes and dictionary keys and values to be used simultaneously and interchangeably.

Peter F 93 Dec 01, 2022
CLASSIX is a fast and explainable clustering algorithm based on sorting

CLASSIX Fast and explainable clustering based on sorting CLASSIX is a fast and explainable clustering algorithm based on sorting. Here are a few highl

69 Jan 06, 2023
Final Project for Practical Python Programming and Algorithms for Data Analysis

Final Project for Practical Python Programming and Algorithms for Data Analysis (PHW2781L, Summer 2020) Redlining, Race-Exclusive Deed Restriction Lan

Aislyn Schalck 1 Jan 27, 2022
Decided to include my solutions for leetcode problems.

LeetCode_Solutions Decided to include my solutions for leetcode problems. LeetCode # 1 TwoSum First leetcode problem and it was kind of a struggle. Th

DandaIT04 0 Jan 01, 2022
RLStructures is a library to facilitate the implementation of new reinforcement learning algorithms.

RLStructures is a lightweight Python library that provides simple APIs as well as data structures that make as few assumptions as possibl

Facebook Research 262 Nov 18, 2022
This repo is all about different data structures and algorithms..

Data Structure and Algorithm : Want to learn data strutrues and algorithms ??? Then Stop thinking more and start to learn today. This repo will help y

Priyanka Kothari 7 Jul 10, 2022
Python collections that are backended by sqlite3 DB and are compatible with the built-in collections

sqlitecollections Python collections that are backended by sqlite3 DB and are compatible with the built-in collections Installation $ pip install git+

Takeshi OSOEKAWA 11 Feb 03, 2022
Svector (pronounced Swag-tor) provides extension methods to pyrsistent data structures

Svector Svector (pronounced Swag-tor) provides extension methods to pyrsistent data structures. Easily chain your methods confidently with tons of add

James Chua 5 Dec 09, 2022
An esoteric data type built entirely of NaNs.

NaNsAreNumbers An esoteric data type built entirely of NaNs. Installation pip install nans_are_numbers Explanation A floating point number is just co

Travis Hoppe 72 Jan 01, 2023
Python tree data library

Links Documentation PyPI GitHub Changelog Issues Contributors If you enjoy anytree Getting started Usage is simple. Construction from anytree impo

776 Dec 28, 2022
A Python library for electronic structure pre/post-processing

PyProcar PyProcar is a robust, open-source Python library used for pre- and post-processing of the electronic structure data coming from DFT calculati

Romero Group 124 Dec 07, 2022
dict subclass with keylist/keypath support, normalized I/O operations (base64, csv, ini, json, pickle, plist, query-string, toml, xml, yaml) and many utilities.

python-benedict python-benedict is a dict subclass with keylist/keypath support, I/O shortcuts (base64, csv, ini, json, pickle, plist, query-string, t

Fabio Caccamo 799 Jan 09, 2023