An evolutionary multi-agent platform based on mesa and NEAT

Related tags

MiscellaneousEvoAgent
Overview

EvoAgent

An evolutionary multi-agent platform based on mesa and NEAT
A video of an old version of EvoAgent can be found on youtube:
https://www.youtube.com/watch?v=pOF1H84xPik&ab_channel=VBiscione

Overview

With this tool you can evolve agents in a simple 2D environments.
At the beginning, agents are endowed with a simple neural network which is specified by their genome. With time, they'll make children, which will inherit the genome, plus some random mutations. The mutations will add a connetion, a node, or change the weight. The evolutionary system is based on NEAT by Kenneth Stanley (paper here). However, the main difference between this approach and the classic evolutionary algorithm approach, is the naturalistic approach we are using here. In a classic evolutionary algorithm we would use a fitness function, we would test our agents, and we would use a genetic operator for generating the next generation. We have none of that here. Agents will spawn a new children every x time-steps. The more they survive, the more children they'll get. I found this approach much more intuitively valid as will simply respond to the rule: the more you survive, the more you'll spread your genes. This will also allow for generational interactions (as multiple generations will live at the same time), in case one wants to run experiments on family behaviour etc.

Install

git clone [email protected]:ValerioB88/EvoAgent.git

EvoAgent plots everything in the browser. This is heavily dependent on the Mesa library. My fork of Project Mesa should be automatically added as a submodule.

Examples

There are several examples in the folder code/evoagent/experiments/, which should get you started. Most of this is self explanatory. For example, run the file difficult_env.py and a browser with the environment view should open. Both the model state and the population gets saved (the model state includes the population). You want to use the model state to continue a running simulation with exactly the same parameters, from exactly the same point (the model state includes the population state). Instead, you may want to test an evolved population on a different enviornment: in that case, load the population. Examples of both these cases in continue_sim.py and load_pop.py. Model and population get saved every 1000 time steps, or when you press s.

Environment View

This contains a canvas, information about the selected agent, and some plots. At each points there always be a selected agents, for which many info are shown in the text field on the right sidebar. You can change the selected agent by pressing a and d on your keyboard (in a future version, it will be possible to click on the agent on the canvas to select it). Other info are shown in the following image:

Shortcuts

q start/stop simulation
a/d previous/next agent
k kill selected agent
c selected agent spawn a child
s save model
x advance the simulation one step

Agents Behaviour

Agents will have a limited field of view, specified by the parameters fov and max_vision_dist. You can visualize them by checking Render FOV in the environment view. Each agent will have a maximum lifespan of max_age = 500, but it can die faster if its energy goes to 0. They have a energy_depletion rate of 0.008. An agent will eat a food token when it touches it, getting an energy increase of 0.8 (or whathever established by the current Epoch, see later), up to 1. Agent will become fertile after fertile_age_start = 90 timesteps. At that point, they will spawn a child every time_between_children = 100 timesteps. For now, reproduction is asexual, so there is no crossover (this will be expanded in a next version).

Agents can only perceive the closest food token, IF it's within their field of view. If the selected agent is perceiving a food token, this will be represented with a red color in the environment view. Agents' network input will be the linear distance to the perceived food token, the angular distance, and their own energy level. There will be two output units, one defining the forward/backward movement, the other one defining the rotation.

Epochs

The epochs are interval of times defined by the amount of food in the environment.

epochs = deque([Epoch(2000, [0.8]*200),
                Epoch(2000, [0.8]*100),
                Epoch(6000, [0.8]*75)])

This means that we have 3 epochs, the first lasting 2000 iteration, the last 6000 iterations. The first will have 200 food tokens, each provigin 0.8 units of energy (recall that [0.8]*200 generates a list of 200 elements of value 0.8: [0.8, 0.8, 0.8....]. By changing the second parametr, you can specify the distribution of food token easily. You can also have "posionous" food: Epoch(2000, [-0.2]*200) this will work. However, currently the agents don't have a way to differentiate between "good" and "bad" food, so it doesn't make much sense to use bad food right now.

The simulation will activate one epoch at the time, starting from the first one. When the last epoch finishes, the simulation stop. You can instead run the simulation indefinitively by setting the epoch duration to np.inf.

Speed Up Simulation

In the environment view, uncheck Render Canvas, then set the Frame per Second slider to 0. That's as fast as it can get!

Known Problems

If you stop the simulation and try to run it again, you'll get the error:
OSError: [WinError 10048] Only one usage of each socket address (protocol/network address/port) is normally permitted
To fix this, try to change the port in server.launch(...). If it doesn't work, close and open your browser. I know this is annoying, but hadn't have the time to fix it yet.

This has only been tested on Windows 10 and Edge 97. I don't plan to test it on any other configuration. Sorry!

To Do

☐ Add sexual reproduction: find a partner, do crossover
☐ Many agents options should be in a config file
☐ Select an agent by clicking on it with the mouse
☐ Implement data collection - or adapt mesa data collection
☐ Implement more ways to perceive food
☐ Implement ways to perceive other agents
☐ Server port stays open after code stops - which often lead to annoying behaviour. Find a way to fix this

Owner
Valerio1988
Valerio1988
Run the Tianxunet software on the Xiaoyao Android simulator

Run the Tianxunet software on the Xiaoyao Android simulator, and automatically fill in the answers of English listening on the premise of having answers

1 Feb 13, 2022
Turn your IPad into a Screen-Slaver with 1 simple Pythonista script

ScreenSlaver Turn your IPad into a Screen-Slaver with 1 simple Pythonista script

6 Jul 09, 2022
This interactive script demonstrates the Menezes-Vanstone-EC-Cryptosystem

Menezes-Vanstone-EC-Cryptosystem This interactive script demonstrates the Meneze

Nishaant Goswamy 1 Jan 02, 2022
Jogo em redes similar ao clássico pedra papel e tesoura

Batalha Tática Tecnologias de Redes de Computadores-A-N-JOGOS DIGITAIS Professor Fabio Henrique Cabrini Alunos: Eric Henrique de Oliveira Silva - RA 1

Eric Henrique de Oliveira Silva 1 Dec 01, 2021
Automated Changelog/release note generation

Quickly generate changelogs and release notes by analysing your git history. A tool written in python, but works on any language.

Documatic 95 Jan 03, 2023
API Rate Limit Decorator

ratelimit APIs are a very common way to interact with web services. As the need to consume data grows, so does the number of API calls necessary to re

Tomas Basham 574 Dec 26, 2022
BlueBorne Dockerized

BlueBorne Dockerized This is the repo to reproduce the BlueBorne kill-chain on Dockerized Android as described here, to fully understand the code you

SecSI 5 Sep 14, 2022
Function Plotter✨

Function-Plotter Build With : Python PyQt5 unittest matplotlib Getting Started This is an list of needed instructions to set up your project locally,

Ahmed Lotfy 3 Jan 06, 2022
pyRTOS is a real-time operating system (RTOS), written in Python.

pyRTOS Introduction pyRTOS is a real-time operating system (RTOS), written in Python. The primary goal of pyRTOS is to provide a pure Python RTOS that

Ben Williams 96 Dec 30, 2022
Script to quickly get the metrics from Github repos to analyze.

commit-prefix-analysis Script to quickly get the metrics from Github repos to analyze. Setup Install the Github CLI. You'll know its working when runn

David Carpenter 1 Dec 17, 2022
Ked interpreter built with Lex, Yacc and Python

Ked Ked is the first programming language known to hail from The People's Republic of Cork. It was first discovered and partially described by Adam Ly

Eoin O'Brien 1 Feb 08, 2022
Additional useful operations for Python

Pyteal Extensions Additional useful operations for Python Available Operations MulDiv64: calculate m1*m2/d with no overflow on multiplication (TEAL 3+

Ulam Labs 11 Dec 14, 2022
Sodium is a general purpose programming language which is instruction-oriented

Sodium is a general purpose programming language which is instruction-oriented (a new programming concept that we are developing and devising)

Satin Wuker 22 Jan 11, 2022
Demo code for "Logs in distributed systems" webinar

Hexlet Logs Demo Пререквизиты docker-compose python3 Учетка в DataDog Базовое понимание, что такое логи (можно почитать гайд

Anton Markelov 1 Dec 01, 2021
An improved version of the common ˙pacman -S˙

BetterPacmanLook An improved version of the common pacman -S. Installation I know that this is probably one of the worst solutions and i will be worki

1 Nov 06, 2021
Blender addon that enables exporting of xmodels from blender. Great for custom asset creation for cod games

Birdman's XModel Tools For Blender Greetings everyone in the custom cod community. This blender addon should finally enable exporting of custom assets

wast 2 Jul 02, 2022
Repo to store back end infrastructure for Message in a Bottle

Message in a Bottle Backend API RESTful API for Message in a Bottle frontend application consumption. About The Project • Tools Used • Local Set Up •

4 Dec 05, 2021
flake8 plugin which forbids match statements (PEP 634)

flake8-match flake8 plugin which forbids match statements (PEP 634)

Anthony Sottile 25 Nov 01, 2022
PressurePlate is a multi-agent environment that requires agents to cooperate during the traversal of a gridworld.

PressurePlate is a multi-agent environment that requires agents to cooperate during the traversal of a gridworld. The grid is partitioned into several rooms, and each room contains a plate and a clos

Autonomous Agents Research Group (University of Edinburgh) 6 Dec 03, 2022
Fused multiply-add (with a single rounding) for Python.

pyfma Fused multiply-add for Python. Fused multiply-add computes (x*y) + z with a single rounding. Useful for dot products, matrix multiplications, po

Nico Schlömer 18 Nov 08, 2022