Repository hosting code used to reproduce results in "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152, I…

🤗 LeRobot: End-to-end Learning for Real-World Robotics in Pytorch

The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization

Robust recipes to align language models with human and AI preferences

Code for "Learning to Model the World with Language."

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

RLHF implementation details of OAI's 2019 codebase

Reinforcement learning resources curated

Generative Agents: Interactive Simulacra of Human Behavior

精选机器学习，NLP，图像识别， 深度学习等人工智能领域学习资料，搜索，推荐，广告系统架构及算法技术资料整理。算法大牛笔记汇总

搜索、推荐、广告、用增等工业界实践文章收集（来源：知乎、Datafuntalk、技术公众号）

MTM Masked Trajectory Models for Prediction, Representation, and Control.

Implementation of Dreamer v3 in pytorch.

Open Bandit Pipeline: a python library for bandit algorithms and off-policy evaluation

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

Mastering Diverse Domains through World Models

Accompanies and reproduces results from the paper "Control Variates for Slate Off-Policy Evaluation"

The simplest, fastest repository for training/finetuning medium-sized GPTs.

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Train transformer language models with reinforcement learning.

【浅梦学习笔记】文章汇总:包含 排序&CXR预估，召回匹配，用户画像&特征工程，推荐搜索综合 计算广告，大数据，图算法，NLP&CV，求职面试 等内容

Foundation Architecture for (M)LLMs

Python implementations of contextual bandits algorithms

The Fuzzy Labs guide to the universe of open source MLOps

Recommendations at "Reasonable Scale": joining dataOps with recSys through dbt, Merlin and Metaflow

Behavioral "black-box" testing for recommender systems

This is the official implementation for the paper: "CIRS: Bursting Filter Bubbles by Counterfactual Interactive Recommender System"

An up-to-date, comprehensive and flexible recommendation library

Hands-on tutorials at EEML2022 summer school