saikrishna-1996

mojo

The Mojo Programming Language

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

the-algorithm-ml

Source code for Twitter's Recommendation Algorithm

the-algorithm

Source code for Twitter's Recommendation Algorithm

awesome-RLHF

A curated list of reinforcement learning with human feedback resources (continually updated)

cogment-verse

Research platform for Human-in-the-loop learning (HILL) & Multi-Agent Reinforcement Learning (MARL)

RLHive

cogment-doc

Cogment official website and documentation

cogment

Cogment platform, Cogment is the first open source platform designed to address the challenges of continuously training humans and AI together.

cogment-py-sdk

Cogment Python SDK

cogment-tutorial-rps

Cogment tutorial

cogment-js-sdk

Cogment Javascript SDK

cogment-model-registry

Now part of https://github.com/cogment/cogment

DeepRL-Tutorials

Contains high quality implementations of Deep Reinforcement Learning algorithms written in PyTorch

rlstructures

RLStructures is a library to facilitate the implementation of new reinforcement learning algorithms. It includes a library, a tutorial, and different RL algorithms provided as examples.

LaMCTS

The release codes of LA-MCTS with its application to Neural Architecture Search.

GenerativeLEGO

Code implementation for the paper "Building LEGO Using Deep Generative Models of Graphs"

dal

Repository for Deep Active Localization research and benchmarks

gradslam

gradslam is an open source differentiable dense SLAM library for PyTorch

max-bellman-toy

Code for gold mining environment described in the "Maximum Reward Formulation In Reinforcement Learning" paper

Apollo1060

Data and models (with prediction scripts) used in publications related to Apollo1060 platform

stockfish

Integrates the Stockfish chess engine with Python

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

tqc_pytorch

Implementation of Truncated Quantile Critics method for continuous reinforcement learning. https://bayesgroup.github.io/tqc/

RLMM

RLMM is a reinforcement learning env for molecular modeling (currently only protein-ligand docking).

allie

Allie: A UCI compliant chess engine

deep_pepper_chess

different AI algorithms to solve board games

QCNN

quantum convolutional neural network - simulations

rlpyt

Reinforcement Learning in PyTorch

nest-vae

PGM projects