Policy Iteration for Continuous Dynamics

This project implements the classic Snake game with a reinforcement learning agent that learns how to play using a Replay Q-Network (RQN) and Linear Q-Learning. The agent is trained through trial and error by receiving rewards for beneficial actions and penalties for harmful actions

This repository implements Q-Learning in Blackjack, comparing it with random action selection and basic strategies. Includes experiments with various strategies, rule variations, and deck numbers to evaluate performance.

Based on the book --- Reinforcement Learning: An Introduction (2nd ed, 2018) by Sutton and Barto. For the Reinforcement Learning course Assignment 3 (see Gridworld Problem 2.pdf) at Memorial University of Newfoundland, Jul. 18, 2024

Based on the book --- Reinforcement Learning: An Introduction (2nd ed, 2018) by Sutton and Barto. For the Reinforcement Learning course Assignment 2 (see Gridworld Problem 1.pdf) at Memorial University of Newfoundland, Jul. 18, 2024

Projects and Models built in Python leveraging PyTorch, implementing Reinforcement Learning algorithms for reward-based tasks.

Dynamic Optimization project working on an economic model

A GPU-accelerated toolbox for hyperbolic PDEs in a weaker (viscosity) sense. It leverages the integral to the solution of the conservation of momentum problem (being equivalent to the derivative of Hamilton-Jacobi equations) in one spatial dimension. We resolve such hyperbolic differential equations using wave-front propagating schemes on a spat…

Provides methods to efficiently set up and solve dynamic programming problems of one choice variable using Value Function Iteration and the Endogenous Grid Method.

My Grid World Application. Presented in class on April 7th, 2023.

Source files of the course "Mathematics for Macroeconomics"

PyDiffGame is a Python implementation of a Nash Equilibrium solution to Differential Games, based on a reduction of Game Hamilton-Bellman-Jacobi (GHJB) equations to Game Algebraic and Differential Riccati equations, associated with Multi-Objective Dynamical Control Systems

Repository for the code of the "Dynamic Programming and Optimal Control" (DPOC) lecture at the "Institute for Dynamic Systems and Control" at ETH Zurich.

Simulation of Routing Algorithms used in communication networks in python

This project aims to explore the basic concepts of Reinforcement Learning using the FrozenLake environment from the OpenAI Gym library.

Mountain Car is a Gym environment. I used this environment to train my model using Q-Learning which is a reinforcement learning technic.

Jupyter notebooks implementing Reinforcement Learning algorithms in Numpy and Tensorflow

This repository contains a variety of projects related to reinforcement learning, showcasing different approaches to implementing it in various scenarios.