Rajkumar Ramamurthy

rllm. Democratizing Reinforcement Learning for LLMs

ART. Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

search-and-learn. Recipes to scale inference-time compute of open models

wildguard. Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

MoRA. MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning

drpo. Dateset Reset Policy Optimization

outlines. Structured Outputs

llm-swarm. Manage scalable open LLM inference endpoints in Slurm clusters

tril. Python

al-folio. A beautiful, simple, clean, and responsive Jekyll theme for academics

InteractiveTextGeneration. Python

BIG-bench. Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

peft. 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

composer. Supercharge Your Model Training

fluidml. FluidML is a lightweight framework for developing machine learning pipelines.

dialog-eval. Evaluate your dialog model with 17 metrics! (see paper)

remote-jobs. Source for remoteintech.company — a community-maintained directory of remote-friendly tech companies

language. Shared repository for open-sourced projects from the Google AI Language team.

WebShop. [NeurIPS 2022] 🛒WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents

pixel. Research code for pixel-based encoders of language (PIXEL)

pomdp-baselines. Simple (but often Strong) Baselines for POMDPs in PyTorch, ICML 2022

zenml. ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.

cog. Containers for machine learning

arxiv-latex-cleaner. arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

RL4RS. A Real-World Benchmark for Reinforcement Learning based Recommender System

GEM-metrics. Automatic metrics for GEM tasks

leaqi. Active Imitation Learing with Noisy Guidance

metadict. MetaDict is a powerful dict subclass enabling (nested) attribute-style item access/assignment and IDE autocompletion support.

reinforcement-learning-an-introduction. Python Implementation of Reinforcement Learning: An Introduction

haystack. Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

annoy. Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

TextRL. Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-176B/bloom/gpt/bart/T5/MetaICL)

awesome-rl-nlp. Curated Reinforcement Learning Resources for Natural Language Processing

tianshou. An elegant PyTorch deep reinforcement learning library.

url_benchmark. Python

esn-for-named-entity-recognition. Python

SimCSE. [EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

applied-ml. 📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

torchtyping. Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.

SSRL. Self-Supervised Reinforcement Learning

dl-visuals. Over 200 figures and diagrams of the most popular deep learning architectures and layers FREE TO USE in your blog posts, slides, presentations, or papers.

alfworld. ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

rl-exploration. Reinforcement Learning papers on exploration methods.

Chrome-T-Rex-Rush. A python remake of the famous T-Rex game from Google chrome

RL4Recsys. paper list in the area of reinforcenment learning for recommendation systems

dataset-sts. Semantic Text Similarity Dataset Hub

awesome-public-datasets. A topic-centric list of HQ open datasets.

trl. Train transformer language models with reinforcement learning.

ecco. Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, BERT, RoBERTA, T5, and T0).

deep-learning-project-template. Pytorch Lightning code guideline for conferences

TD3. Author's PyTorch implementation of TD3 for OpenAI gym tasks

autonomous-learning-library. A PyTorch library for building deep reinforcement learning agents.

pfrl. PFRL: a PyTorch-based deep reinforcement learning library

procgen. Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments

code-for-paper. Python

SLM-Lab. Modular Deep Reinforcement Learning framework in PyTorch. Companion library of the book "Foundations of Deep Reinforcement Learning".

Griddly. A grid-world game engine for game AI research

simple-bert. A simple PyTorch implementation of BERT, complete with pretrained models and training scripts.

mlgym. Python

outlierhub. Python

PPO-PyTorch. Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch

doccano. Open source annotation tool for machine learning practitioners.

captum. Model interpretability and understanding for PyTorch

stable-baselines3. PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

datastack. a stream-based file storage solution for machine learning datasets.

papers-with-annotations. Research papers with annotations, illustrations and explanations

pg-is-all-you-need. Policy Gradient is all you need! A step-by-step tutorial for well-known PG methods.

minimalRL. Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)

rainbow-is-all-you-need. Rainbow is all you need! A step-by-step tutorial from DQN to Rainbow

text-dedicom-paper. Source code to the paper "Interpretable Topic Extraction and Word Embedding Learning using row-stochastic DEDICOM"

Miniworld. Simple and easily configurable 3D FPS-game-like environments for reinforcement learning

dashifyML. A lightweight tool to manage and track your large scale machine leaning experiments

cleanrl. High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

PySyft. Perform data science on data that remains in someone else's server

RankNet. My (slightly modified) Keras implementation of RankNet and PyTorch implementation of LambdaRank.

reinforcement-learning. Personal experiments on Reinforcement Learning

pytorch-A3C. Simple A3C implementation with pytorch + multiprocessing

packing-unpacking-pytorch-minimal-tutorial. Minimal tutorial on packing and unpacking sequences in pytorch

gym-gridworlds. Gridworld environments for OpenAI gym.

Minigrid. Simple and easily configurable grid world environments for reinforcement learning

PyTorch-RL. PyTorch implementation of Deep Reinforcement Learning: Policy Gradient methods (TRPO, PPO, A2C) and Generative Adversarial Imitation Learning (GAIL). Fast Fisher vector product TRPO.

rllab. rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

ai-safety-gridworlds. This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.

pytorch-goodies. PyTorch Boilerplate For Research

trpo. Trust Region Policy Optimization with TensorFlow and OpenAI Gym

ml-agents. The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.

dm_control. Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

practical-pytorch. Go to https://github.com/pytorch/tutorials - this repo is deprecated and no longer maintained

evostra. A fast Evolution Strategy implementation in Python

reinforcement-learning. Minimal and Clean Reinforcement Learning Examples

stochsearch. Stochastic search algorithms using python multiprocessing

spsa. Simultaneous perturbation stochastic approximation Python code

climin. Optimizers for machine learning

pytorch-examples. Simple examples to introduce PyTorch

pytorch.rl.learning. for learning reinforcement learning using PyTorch.

PyTorch-Tutorial. Build your neural network easy and fast, 莫烦Python中文教学