Comparison of RL algorithms (Bandit, Q-Learning etc.) to similar algorithms that use inference. Psi-Auto as an algorithm that automatically tunes the inverse temperature.

Repository for a personal project implementing MPC on spacecraft relative motion models.

A toolbox for the fuel-optimization of space trajectories

A universal wrapper for reinforecement learning agents with guarantees

Assignment for optimal control (MAE 546): Moon Lander Problem

Learning efficient goal-conditioned policies by imitating optimal trajectories

Optimal control for transport-dominated systems with sPOD

python lib for linear quadratic control

Trajectory planning and Control of a 2-dof under actuated robotic arm. University project for the course of Optimal Control.

Code for paper "Co-state Neural Network for Real-time Nonlinear Optimal Control with Input Constraints" at ACC 2025

Code written for the BSc Project: Estimating Control Landscapes with Neural Networks by Susan Chen and Katie Xiao as part of our Imperial College London Physics degrees.

Examples of finite-horizon optimal control problems implemented as environments for reinforcement learning algorithms

Trajectory tracking with stochastic optimal control.

An AI agent trained with Deep Reinforcement Learning (SAC + HER) to solve the FetchPickAndPlace-v4 'pick and place' task in the MuJoCo simulator.

Implementation of an infinite-horizon SSP solver via Policy Iteration to minimize control effort in a stochastic environment. Coursework for ETH Zurich DPOC Fall 2025.

Code for paper "Neural Co-state Regulator: A Data-Driven Paradigm for Real-time Optimal Control with Input Constraints" at CDC 2025

[ICC '21] MACRO: Megastructure Assembly via Collaborative Robots in Orbits

A Reinforcement Learning project that solves the classic CartPole environment using the PPO algorithm for optimal control.