A simple wrapper to analyse and visualise reinforcement learning agents' behaviour in the environment.

Overview

Visrl

Visrl (pronounced "visceral") is a simple wrapper to analyse and visualise reinforcement learning agents' behaviour in the environment.

Reinforcement learning requires a lot of overhead code to inspect an agent's behaviour visually, typically through env.render(). Visrl allows users to easily intervene and switch between agent control and human control, and allows inserting a breakpoint in the game state to pause only at a relevant state of interest.

Features

  • Set action hotkeys
  • Human intervention: Take actions 1 step at a time
  • Agent control: Return control to the agent
  • Speed up/ slow down frame rate
  • Visualise relevant values across history
  • Breakpoint: Run until a condition involving values is fulfilled
  • Playback: Show past frames and ations
  • Record: Record a .mp4, .gif or download a .csv of the history.

Install

pip install visrl

Usage

import gym
from stable_baselines3 import DQN
from visrl import Visrl

env = gym.make('LunarLander-v2')
agent = DQN('MlpPolicy', env, verbose=1)
agent.learn(total_timesteps=int(2e5))

Visrl(env, agent).run()
Owner
Jet New
I currently research model-based multi-agent reinforcement learning and hierarchical multi-agent reinforcement learning.
Jet New
A web application (with multiple API project options) that uses MariaDB HTAP!

Bookings Bookings is a web application that, backed by the power of the MariaDB Connectors and the MariaDB X4 Platform, unleashes the power of smart t

MariaDB Corporation 4 Dec 28, 2022
This alerts you when the avalanche score a goal

This alerts you when the avalanche score a goal

Davis Burrill 1 Jan 15, 2022
This is a simple leaderboard for 30 days of Google Cloud program for students of ASIET

30daysleaderboard #Hacktoberfest - Please don't make changes in readme file. Only improvement in the project will be accepted. Update - Now if you run

5 Oct 29, 2021
All you need to understand CRUD and MVP in DRF

Book-Store-API This an API which has been put in place just to make you order for books, upload books with price, image and all, pay and automtically

Oladipo Adesiyan 6 Jul 03, 2022
Snek-test - An operating system kernel made in python and assembly

pythonOS An operating system kernel made in python and assembly Wait what? It us

TechStudent10 2 Jan 25, 2022
Use Fofa、shodan、zoomeye、360quake to collect information(e.g:domain,IP,CMS,OS)同时调用Fofa、shodan、zoomeye、360quake四个网络空间测绘API完成红队信息收集

Cyberspace Map API English/中文 Development fofaAPI Completed zoomeyeAPI shodanAPI regular 360 quakeAPI Completed Difficulty APIs uses different inputs

Xc1Ym 61 Oct 08, 2022
Inverted-pendulum-with-fuzzy-control - Inverted pendulum with fuzzy control

Fuzzy Inverted Pendulum Basically, this project consists of an inverted pendulum

Mahan Ahmadvand 1 Aug 25, 2022
The fundamentals of Python!

The fundamentals of Python Author: Mohamed NIANG, Staff ML Scientist Presentation This repository contains notebooks on the fundamentals of Python. Th

Mohamed NIANG 1 Mar 15, 2022
A script where you execute a script that generates a base project for your gdextension

GDExtension Project Creator this is a script (currently only for linux) where you execute a script that generates a base project for your gdextension,

Unknown 11 Nov 17, 2022
CaskDB is a disk-based, embedded, persistent, key-value store based on the Riak's bitcask paper, written in Python.

CaskDB - Disk based Log Structured Hash Table Store CaskDB is a disk-based, embedded, persistent, key-value store based on the Riak's bitcask paper, w

886 Dec 27, 2022
Streamlit component to display topics from Streamlit's community forum related to any exception.

streamlit-forum Streamlit component to display topics from Streamlit's community forum related to any exception. Installation pip install streamlit-fo

Snehan Kekre 7 Jul 15, 2022
Traductor de webs desde consola usando el servicio de Google Traductor.

proxiGG Traductor de webs desde consola usando el servicio de Google Traductor. Se adjunta el código fuente para Python3 y un binario compilado en C p

@as_informatico 2 Oct 20, 2021
Web service which feeds Navitia with real-time disruptions

Chaos Chaos is the web service which can feed Navitia with real-time disruptions. It can work together with Kirin which can feed Navitia with real-tim

KISIO Digital 7 Jan 07, 2022
Remote Worker

Remote Worker Separation of Responsibilities There are several reasons to move some processing out of the main code base for security or performance:

V2EX 69 Dec 05, 2022
Projeto job insights - Projeto avaliativo da Trybe do Bloco 32: Introdução à Python

Termos e acordos Ao iniciar este projeto, você concorda com as diretrizes do Código de Ética e Conduta e do Manual da Pessoa Estudante da Trybe. Boas

Lucas Muffato 1 Dec 09, 2021
How did Covid affect businesses?

NYC_Business_Analysis How did Covid affect businesses? COVID's effect on NYC businesses We all know that businesses in NYC have been affected by COVID

AK 1 Jan 15, 2022
The FLARE team's open-source library to disassemble Common Intermediate Language (CIL) instructions.

dncil is a Common Intermediate Language (CIL) disassembly library written in Python that supports parsing the header, instructions, and exception hand

MANDIANT 95 Jan 08, 2023
UdemyPy is a bot that hourly looks for Udemy free courses and post them in my Telegram Channel: Free Courses.

UdemyPy UdemyPy is a bot that hourly looks for Udemy free courses and post them in my Telegram Channel: Free Courses. How does it work? For publishing

88 Dec 25, 2022
Scrapper For Paste.pics

PrntScScrapper Scrapper for Paste.pics If you are bored you can find some random screenshots from prnt.sc Features Saving screenshots Open in Browser

Fareusz 1 Dec 29, 2021
Notes on the Deep Learning book from Ian Goodfellow, Yoshua Bengio and Aaron Courville (2016)

The Deep Learning Book - Goodfellow, I., Bengio, Y., and Courville, A. (2016) This content is part of a series following the chapter 2 on linear algeb

hadrienj 1.7k Jan 07, 2023