A GUI-based idle game maker in progress, where users are able to create idle games through an intuitive GUI, play them, and (eventually) share them with other players online.

Enhanced ChatGPT Clone: Features Anthropic, AWS, OpenAI, Assistants API, Azure, Groq, o1, GPT-4o, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, langchain, DALL-E-3, ChatGPT Plugins, OpenAI Functions, Secure Multi-User System, Presets, completely open-source for self-hosting. Actively in public development.

Simple model-free reinforcement learning agents, a simple equation solver, and Coursera ML assignments

Slay the Spire Mod. Make Claw duplicate like Anger.

Concise, modular implementation of Multi-Scale Convolutional Recurrent Encoder Decoder: https://arxiv.org/abs/1811.08055

A Telegram bot for voice-to-voice conversations with AI built with Vocode

Open source code of Flux Schedule. 2018 published App Store description: https://appadvice.com/app/flux-speed-schedules/1336300102. See Youtube link for demo.

Human Philosophy blog

ext2 File System in C, from inodes to terminal commands, with WSU's KC Wang’s textbook

A Hearthstone environment for reinforcement learning agents, subclassing OpenAI/Gym. Supports human input, and includes a default agent.

Increased the efficiency of GPT-2 by one pass/token per prompt. See https://github.com/openai/gpt-2/pull/119. Code for the paper "Language Models are Unsupervised Multitask Learners"

Build and train PyTorch models and connect them to the ML lifecycle using Lightning App templates, without handling DIY infrastructure, cost management, scaling, and other headaches.

Mini DL Library with eager automatic differentiation. Supports backpropagation over a dynamically built graph.

No description provided.

No description provided.

TicTacToe React tutorial

MineRL Competition for Sample Efficient Reinforcement Learning - Python Package

Experiments modifying GPT-2 for classification, in Google Colab. One-click reproducible

Using this Mathematical ANIMation engine and rewriting Euclidean proofs in 2D form.

Simple text-based game

Subspace Outlier Detection in Linear Time with Randomized Hashing. Code of the paper http://charuaggarwal.net/linearout.pdf

Expert Transfer Learning plays Minecraft, using Pytorch. Back-tracks in expert demonstrations to determine exactly where items are located in field of view.

A collection of anomaly detection methods (iid/point-based, graph and time series) including active learning for anomaly detection/discovery, bayesian rule-mining, description for diversity/explanation/interpretability. Analysis of incorporating label feedback with ensemble and tree-based detectors. Includes adversarial attacks with Graph Convolutional Network.

PyTorch & Rainbow for Obstacle Tower Challenge

practicing applying and modifying RL

PyTorch Implementation of Distributed Prioritized Experience Replay(Ape-X)

Rainbow: Combining Improvements in Deep Reinforcement Learning

U.S. localization fork of ikeyasu's docker-marlo

Marlo environment on headless server

Project Malmo is a platform for Artificial Intelligence experimentation and research built on top of Minecraft. We aim to inspire a new generation of research into challenging new problems presented by this unique environment. --- For installation instructions, scroll down to *Getting Started* below, or visit the project page for more information: