Pinned Repositories
cma_mae
A python implementation of Covariance Matrix Adaptation MAP-Annealing
dqd
A python implementation of differentiable quality diversity.
dqd-rl
Official implementation of "Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learning"
dsage
Implementation of Deep Surrogate Assisted Generation of Environments
MarioGAN-LSI
An experimental setup for running quality diversity algorithms on GAN latent spaces.
milp_constrained_gan
Using MILP to encode constraints of generated game levels.
overcooked_env_gen
Official implementation of the paper "On the Importance of Environments in Human-Robot Coordination", published in RSS 2021.
pyribs
A bare-bones Python library for quality diversity optimization.
scaling-cma-mae
Official implementation of "Training Diverse High-Dimensional Controllers by Scaling Covariance Matrix Adaptation MAP-Annealing"
wecook_assets
ICAROS's Repositories
icaros-usc/pyribs
A bare-bones Python library for quality diversity optimization.
icaros-usc/dqd
A python implementation of differentiable quality diversity.
icaros-usc/dqd-rl
Official implementation of "Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learning"
icaros-usc/overcooked_env_gen
Official implementation of the paper "On the Importance of Environments in Human-Robot Coordination", published in RSS 2021.
icaros-usc/milp_constrained_gan
Using MILP to encode constraints of generated game levels.
icaros-usc/cma_mae
A python implementation of Covariance Matrix Adaptation MAP-Annealing
icaros-usc/dsage
Implementation of Deep Surrogate Assisted Generation of Environments
icaros-usc/scaling-cma-mae
Official implementation of "Training Diverse High-Dimensional Controllers by Scaling Covariance Matrix Adaptation MAP-Annealing"
icaros-usc/EvoStone2
Official implementation of the paper "Deep Surrogate Assisted MAP-Elites for Automated Hearthstone Deckbuilding", published in GECCO 2022.
icaros-usc/wecook_assets
icaros-usc/wecook
A platform for long horizontal robotic manipulation and human-robot collaboration research
icaros-usc/aikido
icaros-usc/dsas
Code for the paper "Surrogate Assisted Generation of Human-Robot Interaction Scenarios"
icaros-usc/libada
icaros-usc/icaros-usc.github.io
Website for the ICAROS Lab. If you find an error on the website, please raise an issue -- this repo is auto-generated, so we can't accept PRs. Enjoy!
icaros-usc/lggltl
Language Grounding with GLTL Formulas
icaros-usc/libhuman
icaros-usc/LSI-Mario-Level-Generation
This page contains supplemental materials of AAAI-21 submission Illuminating Mario Scenes in the Latent Space of a Generative Adversarial Network, including GAN-generated Mario levels, archives of elites using multiple latent-space exploration algorithms, and levels & video playthroughs used in user studies.
icaros-usc/LSI-User-Study
icaros-usc/MAB_Fairness
icaros-usc/minimax
Efficient baselines for autocurricula in JAX.
icaros-usc/mouse_as_joystick
Wrapper to read from a mouse (e.g. bluetooth mouse) and publish ros messages
icaros-usc/mujoco-py
MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.
icaros-usc/overcooked_lsi_user_study
icaros-usc/overcooked_lsi_videos
icaros-usc/pr_assets
icaros-usc/pyribs.org
The pyribs home page
icaros-usc/relaxed_ik
RelaxedIK Solver
icaros-usc/SabberStone
Just another Hearthstone Simulator in C# .Net Core, with some A.I. approaches!
icaros-usc/sphinx-toolbox
Box of handy tools for Sphinx 🧰 📔