Open-source alternatives to Jumanji

ChainerRL is a deep reinforcement learning library built on top of Chainer.

OpenRLHF is a training framework and alignment library designed for reinforcement learning from human feedback across distributed GPU clusters. It provides tools for aligning large language models and multimodal vision-language models using algorithms such as PPO, GRPO, and DPO. The framework distinguishes itself through a distributed inference engine that overlaps sample rollout with training to increase throughput. It supports scaling to models exceeding 70 billion parameters via parameter sharding and handles long-context sequences through ring-attention sequence parallelism. The project

RLinf is a distributed reinforcement learning orchestrator and embodied AI training framework. It provides the infrastructure to train vision-language-action models and robotic policies using a combination of reinforcement learning and supervised fine-tuning. The system is designed for scaling workloads across GPU clusters, managing the placement of actors, rollout workers, and environment components. It features a specialized robotics data collection pipeline for gathering teleoperated demonstrations and simulation trajectories into standardized replay buffers, alongside a hardware interface

Persistent advantage learning dueling double DQN for the Arcade Learning Environment

ROLL is a distributed reinforcement learning framework and model alignment toolkit designed for large language models. It serves as a scalable training pipeline and GPU cluster manager, providing the infrastructure to align model behavior using reinforcement learning algorithms and preference optimization techniques. The project distinguishes itself through an agentic rollout orchestrator that generates and collects multi-turn interaction trajectories between AI agents and simulated environments. It supports specialized alignment methods including Direct Preference Optimization, reinforcement

Minimal and Clean Reinforcement Learning Examples

verl is a distributed training system designed for large language model alignment and reinforcement learning. It provides a framework for executing post-training pipelines, including supervised fine-tuning and reinforcement learning from human feedback, to refine model behavior and agentic capabilities. The system utilizes a hybrid training and inference engine that optimizes memory and communication when switching between model generation and gradient updates. It supports multi-modal reinforcement learning for models processing both image and text data, and implements algorithms such as PPO

Deep Reinforcement Learning library for humans

SLIME is a distributed reinforcement learning framework for large language model post-training that bridges Megatron training with SGLang inference servers. It orchestrates scalable RL loops across GPU clusters, decoupling training and inference into independent processes that communicate over HTTP and NCCL for independent scaling and fault tolerance. The system supports multi-agent reinforcement learning workflows with parallel agent instances, customizable rollout strategies, and personalized agent serving that improves models from prior conversations without disrupting API serving. The fra

Code for the Black-DROPS algorithm: "Black-Box Data-efficient Policy Search for Robotics", IROS 2017/ICRA 2018

This library provides a comprehensive framework for fine-tuning, aligning, and distilling transformer-based language models. It serves as a toolkit for adapting models to specialized domains through supervised learning, while offering advanced methodologies to improve output quality and reasoning capabilities. The project distinguishes itself through specialized alignment and optimization techniques, including direct preference optimization and reinforcement learning, which allow models to be tuned against human preferences without complex reward modeling. It further supports training efficie

A deep Q learning demonstration using Google Tensorflow

AReaL is a system for agent orchestration, distributed model training, and parameter-efficient tuning. It provides a framework for developing multi-turn reasoning agents and training large models using reinforcement learning from human feedback. The project implements a toolkit for improving the visual reasoning and geometry problem solving capabilities of vision-language models. It utilizes a memory-efficient tuning system to optimize mathematical and reasoning models across different inference backends. The infrastructure supports large-scale training through tensor, pipeline, and expert p

Reinforcement Learning in Go

Habitat-Lab is an open-source platform for training and evaluating embodied AI agents in photorealistic 3D indoor environments. It functions as a high-performance 3D indoor environment simulator that supports physics-based interaction, enabling research into navigation and manipulation tasks. The platform provides a modular task-environment abstraction that separates task logic from environment simulation, using configuration-driven pipeline assembly to compose simulation and training pipelines. It includes a hierarchical sensor-actuator architecture for mixing and matching perception and act

A replica of the AlphaZero methodology for deep reinforcement learning in Python

This repository provides supplementary material for our paper Constitutional AI: Harmlessness from AI Feedback.

Welcome to drlzh.ai: a hands-on deep reinforcement learning course where you build the algorithms, not just read about them.

⚡️A Blazing-Fast Python Library for Ranking Evaluation, Comparison, and Fusion 🐍

Accelerated RL

|tests| |pypi| |docs| |License|

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

Tensorflow Keras OpenAI Gym implementation of 1-step Q Learning from "Asynchronous Methods for Deep Reinforcement Learning"

This repository contains the implementation of DISCERN in Python. You can download the manuscript from my website or arXiv.