Open-source alternatives to Atari

Modularized Implementation of Deep RL Algorithms in PyTorch

Baselines is a comprehensive suite of frameworks for reinforcement learning algorithm implementation, imitation learning, and training orchestration. It provides a library of standardized learning algorithms used to benchmark and replicate research results, alongside a deep learning policy framework for constructing neural network architectures such as multi-layer perceptrons, convolutional networks, and long short-term memory networks. The project includes a specialized imitation learning toolkit that enables agents to mimic expert behavior through behavior cloning and generative adversarial

Dopamine is a reinforcement learning research framework designed for prototyping and testing algorithms across diverse simulated environments. It provides an agent development toolkit that utilizes a flat class hierarchy to facilitate the creation and extension of learning agents. The framework includes a standardization layer via environment wrappers that connect agents to various physics simulations and gaming environments. It also features a high-performance experience replay buffer for storing and sampling transition data to improve training stability, alongside a dedicated hyperparameter

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

Julia code for the book Reinforcement Learning An Introduction

Solutions of Reinforcement Learning, An Introduction

LLM Reasoners is a library to enable LLMs to conduct complex reasoning, with advanced reasoning algorithms. It approaches multi-step reasoning as planning and searches for the optimal reasoning chain, which achieves the best balance of exploration vs exploitation with the idea of "World Model"…

Agent Lightning is an optimization framework designed to refine the performance of individual AI agents within complex multi-agent systems. It provides a platform for improving decision-making and task execution by applying reinforcement learning, supervised fine-tuning, and automated prompt optimization. The framework distinguishes itself through its ability to isolate specific agents for targeted tuning, allowing developers to enhance individual behaviors while maintaining the stability of the broader system architecture. By utilizing a modular interface, it integrates with diverse agent fr

MM-EUREKA: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

Documentation | Discussions | Contributing

VLM-R1 is a reasoning vision-language model and embodied AI framework designed to map visual inputs and language instructions into physical navigation waypoints and robotic actions. It functions as a multimodal policy optimizer and an open vocabulary detector capable of locating objects based on arbitrary natural language descriptions. The system distinguishes itself through the use of chain-of-thought reasoning and reinforcement learning to solve complex visual and spatial tasks. It utilizes a video semantic memory system, which employs a visual cache to maintain a history of live video for

An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

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

🚀 Reinforcement Learning for Language Agents🌟

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

MLAlgorithms is an educational machine learning algorithm library consisting of core predictive models implemented from scratch in Python. It serves as a reference for developers to study the internal logic and mathematical workings of these models through clean, minimal implementations. The codebase focuses on the study of algorithm implementation and machine learning education, providing a way to understand internal mechanics by building components without relying on heavy external libraries. The project utilizes object-oriented encapsulation and NumPy-based vectorization to manage model s

This project is a Python-based educational framework designed to simulate reinforcement learning algorithms and environments. It serves as a platform for reproducing classic textbook examples, allowing users to study agent behavior, policy improvement, and the fundamental mechanics of decision-making in controlled settings. The library provides implementations for core reinforcement learning concepts, including temporal difference learning, Monte Carlo episode sampling, and tabular value function approximation. It enables the analysis of specific algorithmic behaviors, such as identifying and

📘Tutorial | 🛠️Installation | 🎨Framework

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

Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.

A version of verl to support diverse tool use TMLR 2026