Search Results for "q learning algorithm"

javascript-algorithms is an open source repository by Oleksii Trekhleb that provides implementations of algorithms and data structures in JavaScript. Each algorithm includes explanations, complexity analysis, and references for further reading, making it both a coding resource and a study guide. The repository covers topics such as sorting, searching, graph algorithms, cryptography, and data structures like linked lists, stacks, and queues. It is designed to help developers understand...

javascript-algorithms is a repository that implements a comprehensive collection of classic data structures and algorithmic solutions in JavaScript — including sorting, searching, graph algorithms, dynamic programming, and more. It serves as a learning and reference resource for developers wanting to understand how standard algorithms can be expressed in JavaScript, bridging the gap between theoretical algorithm knowledge and practical implementation usable in web or Node.js contexts. Because algorithms are implemented in a language (JavaScript) many developers use daily, the repo becomes especially useful for students, interview-preparation candidates, or anyone wanting to learn algorithmic thinking without switching languages. ...

This repository is a comprehensive personal journal of LeetCode problem-solving journey. It includes detailed solutions with code, algorithm insights, data structure summaries, Anki flashcards, daily challenge logs, and future planning sections.

The supervised-reptile repository contains code associated with the paper “On First-Order Meta-Learning Algorithms”, which introduces Reptile, a meta-learning algorithm for learning model parameter initializations that adapt quickly to new tasks. The implementation here is aimed at supervised few-shot learning settings (e.g. Omniglot, Mini-ImageNet), not reinforcement learning, and includes scripts to run training and evaluation for few-shot classification. ...

ConvNetJS is a Javascript library for training Deep Learning models (Neural Networks) entirely in your browser. Open a tab and you're training. No software requirements, no compilers, no installations, no GPUs, no sweat. ConvNetJS is an implementation of Neural networks, together with nice browser-based demos. It currently supports common Neural Network modules (fully connected layers, non-linearities), classification (SVM/Softmax) and Regression (L2) cost functions, ability to specify and train Convolutional Networks that process images, and experimental Reinforcement Learning modules, based on Deep Q Learning. ...

...With CSG, you build complex 3D shapes by combining primitives using Boolean operations like union, subtract, and intersect. The library focuses on clarity and correctness: its implementation is intentionally concise and readable so developers can understand the algorithm, while still correctly handling tricky edge cases such as overlapping coplanar polygons. A WebGL-based demo shows how two solids can be combined interactively in the browser, making it a great educational tool for learning CSG concepts. The API allows you to create primitives (cubes, spheres, etc.) and then combine or transform them programmatically, producing new mesh geometry for rendering or export. ...

jsGorithm is a Javascript algorithm execution viewer that can be used as an educative tool for introductory courses on programming and algorithmics, with programs written in a subset of C/C++/Javascript. It can be used for teaching and learning.