Iterative Linear Quadratic Regulator with auto-differentiatiable dynamics models

Implementations in Unity of the Ten Minute Physics YouTube channel. Instead of using Unity's built-in physics engine, you will learn how to make your own. This is useful if you want to simulate ropes, cloth, tires, etc. You will also learn how to make fluid simulations and soft body physics.

Python implementation of MPPI (Model Predictive Path-Integral) controller to understand the basic idea. Mandatory dependencies are numpy and matplotlib only.

iterative Linear Quadratic Regulator with constraints.

A toolbox for trajectory optimization of dynamical systems

Tensorflow implementation of the asynchronous advantage actor-critic (a3c) reinforcement learning algorithm for continuous action space

Animation of the motion a double-pendulum. Both Julia and Python versions of the code are given.

Repositorio de la II Escuela de Verano en Física computacional (100% virtual), donde participaron estudiantes de habla hispana de todo lationamérica.

This repository is for our paper: "The Experimental Multi-Arm Pendulum on a Cart: A Benchmark System for Chaos, Learning, and Control." It contains all the CAD files we used to build the pendulum hardware, their corresponding user's manual, and data set we collected from our hardware, which is useful for Machine Learning and AI community.

Open AI Gym - Pendulum-v1 reinforcement learning (DQN, SAC)

WIP implementation of Probabilistic Differential Dynamic Programming in PyTorch

clear single-file JAX implementations of common RL algorithms

ICalLibrary - Fast, yet simple, iCalendar reader with excellent recurrence support in Python

About fuzzy logic using the Maxwell's pendulum

Code for FLEX, a fast, adaptive and flexible model-based reinforcement learning exploration algorithm.

These are the files for my Reaction Wheel Pendulum project.

Train agents to balance an inverting pendulum

3D pendulum simulation from first principals

Tensorflow implementation of reinforcement learning (PG, A2C, DQN, DDPG, PPO, HER, SAC)

Fully customizable/interactable pendulum simulation with 3 PDE methods and an ability to use none of them. Comes with a GUI; Is easily generalizable. PDE-s derived from MatLab.