Implementations of various RL and Deep RL algorithms in TensorFlow, PyTorch and Keras.

HIkers est un projet SQL permettant la gestion d'une base de données relationnelle des randonneurs ainsi que tous leur parcours, offrant une interactivité avec l'utilisateur en lui donnant la possibilité d'effectuer des requêtes SQL de son choix .En un petit résumé , il s'agit d'un CRUD SQL/Python.

Independent Project - I joined and manipulated data from disparate tables of movie information using Python & SQLite; defined schema, created tables/views, queried data, etc. Utilized CTE's, Window Functions, and other DDL, DQL, DML, and DCL scripts.

The Double Inverted Pendulum consists of two joint pendulums connected to a cart that is moving on a track, the RL agent needs to keeps in equilibrium the Double Inverted Pendulum.

Query OpenSearch logs and export them to CSV or JSON with high efficiency and speed.

This repository contains code to train and test policies for a MPE environment (Simple Spread). Training is done using DQL for independent learning. Testing was done using 3 different policies: RL, Simple Policy, Complex Policy.

Reinforcement Learning (COMP 579) Course Project

Reinforcement Learning-powered compiler autotuning system that learns optimal flag configurations for performance improvement across PolyBench benchmarks. Includes training, evaluation, and visualization tools.

This project explores Reinforcement Learning on FrozenLake using two approaches: Tabular Q-Learning and Deep Q-Learning with neural networks. It compares classical vs deep RL, includes training, validation, and visualizations, and highlights reward shaping, exploration-exploitation trade-offs, and model performance.

The question-answer paper discusses Data mining techniques in Data Science

Query Made Human.

Play "Google Chrome Dinosaur" game via Deep Q Learning

Human-level control using Deep Reinforcement Learning (deep Q learning) in OpenAI's gym cartpole environment with pytorch

Deep Q-learning (DQL) for playing Snake game

🐍 Implement deep Q-learning to enhance the Snake game experience, enabling smarter gameplay strategies and improved learning performance.

This software is a plugin for the Veusz software. It is designed to load DQL files produced by the X-ray diffractometer D8 Brucker.