Interactive Learning Course | Home Works & Quiz | Fall 2021 | Prof. Majid Nili

c++ implementation of algorithms for solving regret-minimising database queries

A python implementaion of Counterfactual Regret Minimization using numba

This repository contains code for the paper "Non-monotonic Resource Utilization in the Bandits with Knapsacks Problem".

FD-RMS

POMRL: No-Regret Learning-to-Plan with Increasing Horizons [TMLR 2023]

Create a platform that recommends sustainable farming practices to farmers based on their specific location, soil type, crop choice, and climate conditions. Incorporating data on sustainable agriculture methods could help in increasing crop yield, reducing environmental impact, and promoting biodiversity.

Paper implementation of Sequential Learning for Multi-Channel Wireless Network Monitoring With Channel Switching Costs

A visualization of a Regret Minimization Learning algorithm for Two Person games, but Avatar themed! 15-251 Fall 2020 Project

This project is a heads-up no-limit Texas Hold’em solver designed to compute GTO strategies. It leverages CFR with efficient abstractions, allowing scalable strategy computation and analysis. The solver supports range input, action abstraction, and real-time decision-making, making it suitable for both research and practical gameplay analysis

A regret minimization approach to training Generative Adversarial Networks (GANs). This was my project in the "Algorithms and Optimization for Big Data" course.

A Monte Carlo CFR solver for All-In or Fold poker, computing approximate Nash-equilibrium strategies efficiently

Probabilistic Future Video Frame Prediction using Generative Adversarial Networks by employing a regret minimization strategy for training GANs.

This repository contains several implementations of multi-armed bandit (MAB) agents applied to a simulated cricket match where an agent selects among different strategies with the goal of maximizing runs while minimizing the risk of getting out.

Project on preference learning - ENSAE ParisTech

Robust Deep Monte Carlo Counterfactual Regret Minimization: Addressing Theoretical Risks in Neural Fictitious Self-Play

Source code for Regret synthesis for two-player turn-based game played on graphs - ICRA 22

🃏 Build a powerful Heads-Up No-Limit Texas Hold'em solver using Monte Carlo techniques and advanced game analysis for optimal strategy development.