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
A random cat fact python module

A random cat fact python module

Fayas Noushad 4 Nov 28, 2021
Online HackerRank problem solving challenges

LinkedListHackerRank Online HackerRank problem solving challenges This challenge is part of a tutorial track by MyCodeSchool You are given the pointer

Sefineh Tesfa 1 Nov 21, 2021
Convert temps in your Alfred search bar

Alfred Temp Converter Convert temps in your Alfred search bar. Download Here Usage: temp 100f converts to Celsius, Kelvin, and Rankine. temp 100c conv

Justin Hamilton 4 Apr 11, 2022
Get a list of content on your Netflix My List that is expiring in the next month or two.

Netflix My List Expiring Movies Annoyed at Netflix for taking away your movies? Now you don't have to be! Installation instructions Install selenium C

24 Aug 06, 2022
You can easily send campaigns, e-marketing have actually account using cash will thank you for using our tools, and you can support our Vodafone Cash +201090788026

*** Welcome User Sorry I Mean Hello Brother ✓ Devolper and Design : Mokhtar Abdelkreem ========================================== You Can Follow Us O

Mo Code 1 Nov 03, 2021
PIP Manager written in python Tkinter

PIP Manager About PIP Manager is designed to make Python Package handling easier by just a click of a button!! Available Features Installing packages

Will Payne 9 Dec 09, 2022
The bidirectional mapping library for Python.

bidict The bidirectional mapping library for Python. Status bidict: has been used for many years by several teams at Google, Venmo, CERN, Bank of Amer

Joshua Bronson 1.2k Dec 31, 2022
MIT version of the PyMca XRF Toolkit

PyMca This is the MIT version of the PyMca XRF Toolkit. Please read the LICENSE file for details. Installation Ready-to-use packages are available for

V. Armando Solé 43 Nov 23, 2022
30DaysOfCode-PhoenixClub - Solution of everyday coding problem given in 30DaysofCode contest held on Hackerrank

30DaysOfCode-PhoenixClub 👨‍💻 Every day problems solution given in 30DaysOfCode

Urveshkumar 8 Jan 30, 2022
Python dictionaries with advanced dot notation access

from box import Box movie_box = Box({ "Robin Hood: Men in Tights": { "imdb stars": 6.7, "length": 104 } }) movie_box.Robin_Hood_Men_in_Tights.imdb_s

Chris Griffith 2.1k Dec 28, 2022
Wordle Solver

Wordle Solver Installation Install the following onto your computer: Python 3.10.x Download Page Run pip install -r requirements.txt Instructions To r

John Bucknam 1 Feb 15, 2022
GA SEI Unit 4 project backend for Bloom.

Grow Your OpportunitiesTM Background Watch the Bloom Intro Video At Bloom, we believe every job seeker deserves an opportunity to find meaningful work

Jonathan Herman 3 Sep 20, 2021
A cheat sheet for streamlit

Streamlit Cheat Sheet App to summarise streamlit docs v1.0.0 There is also an accompanying png and pdf version https://github.com/daniellewisDL/stream

Daniel Lewis 221 Jan 04, 2023
DeDRM tools for ebooks

DeDRM_tools DeDRM tools for ebooks This is a fork of Apprentice Harper's version of the DeDRM tools. I've added some of the PRs that still haven't bee

2 Jan 10, 2022
sfgp is a package that aggregates individual scripts and notebooks, primarily written for the basic analysis tasks of genetics and pharmacogenomics data.

sfgp is a package that aggregates individual scripts and notebooks, primarily written for the basic analysis tasks of genetics and pharmacogenomics data.

Vishal Sarsani 1 Mar 31, 2022
PythonCalculator - A simple Calculator made in python using tkinter for GUI

PythonCalculator A simple Calculator made in python using tkinter for GUI. For P

ʀᴇxɪɴᴀᴢᴏʀ 1 Jan 01, 2022
A 100% python file organizer. Keep your computer always organized!

PythonOrganizer A 100% python file organizer. Keep your computer always organized! To run the project, just clone the folder and run the installation

3 Dec 02, 2022
Problem statements on System Design and Software Architecture as part of Arpit's System Design Masterclass

Problem statements on System Design and Software Architecture as part of Arpit's System Design Masterclass

Relog 1.1k Jan 04, 2023
Python 3 script for installing kali tools on your linux machine

Python 3 script for installing kali tools on your linux machine

gh0st 2 Apr 20, 2022
Little tool in python to watch anime from the terminal (the better way to watch anime)

anipy-cli Little tool in python to watch anime from the terminal (the better way to watch anime) Has a resume playback function when picking from Hist

sdao 97 Dec 29, 2022