rssalessio

Alessio Russo's repositories

PyDeePC

Python library that implements DeePC: Data-Enabled Predictive Control

Language:PythonMIT42 1 1

algorand-royalty-fees

This is a short tutorial that explains how to implement Royalty Fees using Inner Transactions and Teal v5 capabilities in the Algorand blockchain

Language:PythonMIT15 2 2

This is a collection of interesting papers that I have read so far or want to read. Note that the list is not up-to-date. Topics: reinforcement learning, deep learning, mathematics, statistics, bandit algorithms, optimization.

10 20

PythonVRFT

Virtual Reference Feedback Tuning (VRFT) Python Library - Alessio Russo (alessior@kth.se)

Language:PythonMIT9 3 20

AdaptiveControlLibrary

Matlab implementation of the Adaptive Control Library

Language:MATLABMIT8 10

PyZPC

Python library that implements ZPC: Zonotopic Data-Driven Predictive Control.

Language:PythonMIT8 10

data-poisoning-linear-systems

Code for the paper Analysis and Detectability of Offline Data Poisoning Attacks on Linear Systems.

Language:PythonMIT6 20

TZDDPC

Tube-Based Zonotopic Data Driven Predictive Control

Language:PythonMIT5 10

pyzonotope

Zonotope implementation in python. Supports CVXPY

Language:PythonMIT4 10

SelfTuningTubeBasedMPC

Self-Tuning Tube-Based MPC Controller

Language:PythonMIT4 10

OSRL-SC

OSRL (Optimal Representation Learning in Multi-Task Bandits) comprises an algorithm that addresses the problem of sample complexity with fixed confidence in Multi-Task Bandit problems. Published at the Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI23)

Language:Python3 10

ModelFreeActiveExplorationRL

This repository hosts the code accompanying the paper "Model-Free Active Exploration in Reinforcement Learning". Our study approaches the exploration problem in Reinforcement Learning (RL) from an information-theoretical viewpoint and presents a novel, efficient, and entirely model-free solution.

Language:Jupyter NotebookMIT2 10

optimal-attack-control-channel-mdp

Language:Jupyter NotebookMIT2 10

Py-Data-Driven-Reachability-Analysis

Python implementation of data-driven reachability analysis using Zonotopes

Language:PythonMIT2 10

PyQuadraticFormNormal

Python library that implements the computation of the distribution of a linear combination of non-centered χ2 random variables. Can compute the distribution function of Quadratic Forms in Normal Variables

Language:C++MIT2 10

torch-rl-learnable-environment

The goal of this repository is to provide a gym-compatible library to easily perform model-based Reinforcement Learning experiments using PyTorch. The library makes it easier to create learnable environments and ensembles of networks that can be used to learn the dynamics of an environment.

Language:PythonMIT2 10