This repository contains classwork and practice examples based on Model Predictive Control. Robust and Stochastic control methods applied to and studied for linear/non-linear plants.

HFT & Stochastic control numerical implementations from "Optimal high frequency trading with limit and market orders" (GUILBAUD & PHAM)

Code for thesis project on applying reinforcement learning to algorithmic trading

Paper: Challenges in High-dimensional Reinforcement Learning with Evolution Strategies

Code for the paper {Pang, Bo, and Zhong-Ping Jiang. "Reinforcement Learning for Adaptive Optimal Stationary Control of Linear Stochastic Systems." arXiv preprint arXiv:2107.07788 (2021)."}

Bellman Equation, Pontryagin Maximum Principle, and Deep Learning to solve stochastic control problems

Control + Bellman equation to find arbitrage strategies in Constant Product Market with constant fees

This code can be used to reproduce the results in our paper ``Extended Kalman filter---Koopman operator for tractable stochastic optimal control'.

Code for journal publication 10.1109/OJCSYS.2023.3291596

Master’s project on market making: comparison of stochastic control models (Avellaneda–Stoikov) and reinforcement learning agents across synthetic price processes modeling limit order book environments.

Risk-sensitive asset management simulation in Matlab.

Repository for inference method for stochastic processes through geometric path augmentation

Real-time volatility sensitive detection and correction for any sequential generative process. AutoTune, feedback learning, reflexive analysis, Monte Carlo SDE bands, Kalman filtering, GARCH variance modeling, signal detection, and domain anchoring.

Optimal trade execution using the Almgren–Chriss stochastic control framework with illustrative notebooks.Optimal trade execution using the Almgren–Chriss stochastic control framework with illustrative notebooks.Using Stochastic Control especially the Almgren-Chriss framework

Calibration of Stochastic Volatility models on implied volatility smiles

The goal of this project is to explore and compare the different methods of solving optimal control problems in dynamical systems

This project reimagines the classical Merton portfolio optimization problem using Deep Reinforcement Learning (DRL). Instead of static, closed-form allocation rules, we design an intelligent agent that dynamically adjusts exposures to risky and risk-free assets under changing market regimes.

PID with neural networks

This code can be used to reproduce the results in our paper ``A Control Approach for Nonlinear Stochastic State Uncertain Systems with Probabilistic Safety Guarantees''.

Avellaneda-Stoikov market making framework applied to SPY equity and options. Covers parameter calibration from real market data, Black-Scholes/SABR pricing, delta hedging, and P&L decomposition across 40 simulated trading days.