Ariel Kwiatkowski's repositories
deep-rl-class
This repo contain the syllabus of the Hugging Face Deep Reinforcement Learning Class.
beeware
A meta-package simplifying the installation of the BeeWare suite of tools
daisi-starter-template
Example daisi repository
KDMA
[IROS2021] Human-Inspired Multi-Agent Navigation using Knowledge Distillation
stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
sequential_social_dilemma_games
Repo for reproduction of sequential social dilemmas
SuperSuit
Easy-to-use micro-wrappers for Gym and PettingZoo based RL Environments
sumo-rl
An interface for Reinforcement Learning environments with SUMO for Traffic Signal Control. Compatible with gym, PettingZoo and RLlib.
rl-baselines3-zoo
A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
OpenTraj
Human Trajectory Prediction Dataset Benchmark (ACCV 2020)
Bonquest
A WIP Unity game
typarse
Simple type-based argument parsing
ProgressBars.jl
A Julia clone of https://pypi.python.org/pypi/tqdm
spinningup
An educational resource to help anyone learn deep reinforcement learning.
Ecosystem
RL-powered ecosystem simulation (work in progress)
ray
An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.
rl-pong
Implementation of PPO for playing the game of Pong, originally used in the Reinforcement Learning class at Aalto University
udacity-collaboration-ppo
My implementation of the final project in the Udacity DRL Nanodegree, about Multiagent Reinforcement Learning
udacity-reacher-ppo
My implementation of the second Deep Reinforcement Learning Nanodegree Project
festival_project
Final project for the ID2209 class at KTH
rl_robotics
Code testing reinforcement learning algorithms on robotics problems, for the KTH II2202 course
nodebook-prototype
A barebones backend prototype for nodebook, with an engineer-style frontend. The v2 branch contains a functional API-based version
antworld-0.0
A simple Python implementation of the pheromone-based ant model, adapted from https://practicingruby.com/articles/ant-colony-simulation
battlestax
Repo for the JamStack webinar
dotfiles
Dot files for Evan Chen (Arch Linx on i3)