Coder Social home page Coder Social logo

lamarckism_environments's Introduction

Lamarckian Inheritance Improves Robot Evolution in Dynamic Environments

We tested the Lamarckian system both in the real world and in a MuJoCo-based wrapper called Revolve2. The release version of Revolve2 used in this project is v0.3.8-beta1, available at https://github.com/ci-group/revolve2/releases/tag/v0.3.8-beta1. The setup for the physical experiments can be found here: https://github.com/onerachel/physical_robot_experiments.

Parameters used in the experiments are:

ENVIRONMENT = "FLAT" or "RUGGED" # type of environment
CHANGE_FREQUENCY = 0 or 2 or 5   # frequency of environmental changes during an evolutionary run
pop_size=50,
offspring_size=25,
nr_generations=30,
learner==RevDE,
learning_trials=280

Installation

Steps to install:

1. git clone https://github.com/onerachel/Lamarckism_Environments.git
2. cd Lamarckism_Environments
3. virtualenv -p=python3.8 .venv
4. source .venv/bin/activate
5. ./dev_requirements.sh

In case you have installation errors wrt multineat, find where the cereal library is installed, e.g.: find / -name "cereal*", then tell CPPNWIN where to look for cereal manually, e.g.: export CPATH=/usr/local/include

Run experiments

To run experiments

cd lamarckian_evolution
python optimize.py

To show the simulation, add --visualize:

python optimize.py --visualize

To restart from the last optimization checkpoint, simply rerun:

python optimize.py

To plot fitness:

python plot_fitness.py

To check the best robot wrt the fitness:

python rerun_best.py

To check the best robot wrt the fitness and save the video:

python rerun_best.py -r <OUTPUT-DIR>

Highlighted results

Documentation

ci-group.github.io/revolve2

lamarckism_environments's People

Contributors

onerachel avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.