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
Reproducible nvim completion framework benchmarks.

Nvim.Bench Reproducible nvim completion framework benchmarks. Runs inside Docker. Fair and balanced Methodology Note: for all "randomness", they are g

i love my dog 14 Nov 20, 2022
A curated list of awesome things related to Pydantic! 🌪️

Awesome Pydantic A curated list of awesome things related to Pydantic. These packages have not been vetted or approved by the pydantic team. Feel free

Marcelo Trylesinski 186 Jan 05, 2023
Sentiment Based Product Recommendation System

Sentiment Based Product Recommendation System The e-commerce business is quite p

Sumit Sahay 2 Jan 15, 2022
A python script that fetches the grades of a student from a WAEC result in pdf format.

About waec-result-analyzer A python script that fetches the grades of a student from a WAEC result in pdf format. Built for federal government college

Oshodi Kolapo 2 Dec 04, 2021
Helps compare between New and Old Tax Regime.

Income-Tax-Calculator Helps compare between New and Old Tax Regime. Sample Console Input/Output

2 Jan 10, 2022
A calculator to test numbers against the collatz conjecture

The Collatz Calculator This is an algorithm custom built by Kyle Dickey, used to test numbers against the simple rules of the Collatz Conjecture.

Kyle Dickey 2 Jun 14, 2022
News-app - This is a news web app for reading news from different sources and topics

News-app - This is a news web app for reading news from different sources and topics

1 Feb 02, 2022
Add your recently blog and douban states in your GitHub Profile

Add your recently blog and douban states in your GitHub Profile

Bingjie Yan 4 Dec 12, 2022
Render reMarkable documents to PDF

rmrl: reMarkable Rendering Library rmrl is a Python library for rendering reMarkable documents to PDF files. It takes the original PDF document and th

Robert Schroll 95 Dec 25, 2022
Laurence Billingham 1 Feb 16, 2022
BMI-Calculator: Program to Calculate Body Mass Index (BMI)

The Body Mass Index (BMI) or Quetelet index is a value derived from the mass (weight) and height of an individual, male or female.

PyLaboratory 0 Feb 07, 2022
Zeus is an open source flight intellingence tool which supports more than 13,000+ airlines and 250+ countries.

Zeus Zeus is an open source flight intellingence tool which supports more than 13,000+ airlines and 250+ countries. Any flight worldwide, at your fing

DeVickey 1 Oct 22, 2021
From "fixed RAnDom CRashes" to "[FIX] Fixed random crashes."

Clean Commit From fixed RAnDom CRashes to [FIX] Fixed random crashes. Clean commit helps you by auto-formating your commits to make your repos better

Mathias 3 Dec 26, 2021
This is an online course where you can learn and master the skill of low-level performance analysis and tuning.

Performance Ninja Class This is an online course where you can learn to find and fix low-level performance issues, for example CPU cache misses and br

Denis Bakhvalov 1.2k Dec 30, 2022
Two predictive attributes (Speed and Angle) and one attribute target (Power)

Two predictive attributes (Speed and Angle) and one attribute target (Power). A container crane has the function of transporting containers from one point to another point. The difficulty of this tas

Astitva Veer Garg 1 Jan 11, 2022
SimilarWeb for Team ACT v.0.0.1

SimilarWeb for Team ACT v.0.0.1 This module has been built to provide a better environment specifically for Similarweb in Team ACT. This module itself

Sunkyeong Lee 0 Dec 29, 2021
A python script to get your activity

activities A python script to get your activity Not complete Requirements Python (=3.7) Pip (for python = 3.7) Git Pip packages psutil asyncio aioht

StarNumber 3 Nov 07, 2021
Paimon is a pixie (or script) who was made for anyone from {EPITECH} who are struggling with the Coding Style.

Paimon Paimon is a pixie (or script) who was made for anyone from {EPITECH} who are struggling with the Coding Style. Her goal is to assist you in you

Lyy 2 Oct 17, 2021
A notebook explaining the principle of adversarial attacks and their defences

TL;DR: A notebook explaining the principle of adversarial attacks and their defences Abstract: Deep neural networks models have been wildly successful

1 Jan 22, 2022
Collapse a set of redundant kmers to use IUPAC degenerate bases

kmer-collapse Collapse a set of redundant kmers to use IUPAC degenerate bases Overview Given an input set of kmers, find the smallest set of kmers tha

Alex Reynolds 3 Jan 06, 2022