Name: Alexander Quessy
Type: User
Company: Bristol University
Bio: University of Bristol PhD Student researching Deep Reinforcement Learning and Machine Learning for Aerial Robotics
Location: London, United Kingdom
Blog: https://aos55.github.io
Alexander Quessy's Projects
Aircraft Design Recipes in Python
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
My solution to Airsim Competition at NeuRIPS
Public facing readme for my profile
Personal Research Website
ArduPlane, ArduCopter, ArduRover source
Massively parallel rigidbody physics simulation on accelerator hardware.
A repository containing simulation tools for undergraduate coursework & postgraduate research
Code for 'Dynamics-Aware Unsupervised Discovery of Skills' (DADS). Enables skill discovery without supervision, which can be combined with model-based control.
Implementations of robust Dual Curriculum Design (DCD) algorithms for unsupervised environment design.
DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
Trying to understand the waves
Combines JSBSim and Airsim with a python module to simulate a fixedwing
Mirror: FlightGear - Open source flight sim
An Open Flexible Quadrotor Simulator
A gymnaisum environment for autonomous decision making in fixed-wing aircraft
A toolkit for developing and comparing reinforcement learning algorithms.
The most simple, flexible, and comprehensive OpenAI Gym trading environment (Approved by OpenAI Gym)
A reinforcement learning environment for aircraft control using the JSBSim flight dynamics model
An open source flight dynamics & control software library
Author implementation of LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Iterative Tasks
A PyTorch Library for Meta-learning Research
Library for Model Based RL
Implementation of Efficient Off-policy Meta-learning via Probabilistic Context Variables (PEARL)
Paired Open-Ended Trailblazer (POET) and Enhanced POET
Official Dgraph Python client