Single agent optimization

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

This repository provides a comprehensive library of reinforcement learning algorithms designed for training autonomous agents. It serves as a research-oriented collection of implementations that cover fundamental decision-making strategies, including dynamic programming, temporal difference learning, and policy gradient methods. The project distinguishes itself by offering specialized frameworks for deep reinforcement learning and structured decision modeling. It includes implementations for deep Q-learning that utilize neural networks, experience replay, and prioritized sampling to approxima

OpenManus-RL is a reinforcement learning framework and distributed training pipeline designed to train large language models as agents. It serves as an agentic reasoning optimizer and reward model trainer, providing the infrastructure to improve model decision-making through reward-based policy optimization. The project distinguishes itself through a distributed architecture that supports parameter sharding across multiple compute nodes and a coordinated rollout system for collecting interaction trajectories. It incorporates advanced reasoning strategies, such as Tree-of-Thoughts and Monte Ca

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

This project is a distributed training infrastructure designed for aligning large language models through reinforcement learning. It functions as an end-to-end engine for complex alignment tasks, including proximal policy optimization, direct preference optimization, and iterative self-play. By providing a unified framework for multi-turn interactions and tool-use scenarios, it enables the development of models capable of reasoning and external environment engagement. The framework distinguishes itself through a decoupled architecture that separates model training from sample generation. This

CleanRL is a reinforcement learning library and PyTorch framework providing a suite of reproducible implementations for online reinforcement learning algorithms. It serves as a deep reinforcement learning benchmark suite and experiment orchestrator designed for research and agent development across both discrete and continuous action spaces. The project is distinguished by its single-file algorithm implementation approach, which encapsulates each algorithm in a standalone script to eliminate complex class hierarchies. This structure is paired with a system for scheduling and executing large-s

Stable-baselines3 is a reinforcement learning library built on the PyTorch deep learning framework. It provides a collection of reliable, standardized implementations of reinforcement learning algorithms designed for training, testing, and benchmarking agent policies in diverse simulated environments. The library functions as an agent training toolkit that emphasizes modularity and reproducibility. It features a unified environment interface and supports vectorized execution to accelerate data collection across multiple simulation instances. Users can customize neural network architectures, f

Horizon is a reinforcement learning platform designed for training, evaluating, and deploying agents and contextual bandits using historical data. It serves as an off-policy engine and offline policy evaluation tool, allowing decision-making policies to be optimized and tested without the need for a live simulator. The framework specializes in recommendation system optimization, specifically using slating-based reinforcement learning to optimize the ordering and sequencing of multiple recommendations. It also functions as a contextual bandit framework that manages the balance between explorat

Search-R1 is a distributed training system and reinforcement learning framework designed to create search-augmented language models. It provides an architecture for scaling model workloads across head and worker nodes while optimizing how models interleave internal reasoning with external tool calls. The system focuses on refining model behavior through custom reward signals and reinforcement learning to improve tool-use formatting and information retrieval. It implements an interleaved reasoning-search loop that allows models to alternate between internal thought generation and external data

NNI is an AutoML toolkit designed to automate machine learning lifecycles. It functions as a hyperparameter optimization framework, a neural architecture search tool, and a model compression suite. The project provides a distributed training orchestrator to manage machine learning workloads across local machines, remote servers, and cloud platforms. It enables the discovery of efficient model structures through reinforcement learning and one-shot optimization methods, while utilizing Bayesian and evolutionary algorithms to automate hyperparameter tuning. Additional capabilities include tools

This project is an educational repository of reinforcement learning agents and tutorials implemented using TensorFlow. It provides a practical codebase for both model-free and model-based learning agents, designed to demonstrate how AI agents learn through trial and error. The collection features detailed implementations of various algorithmic approaches, including Deep Q-Networks and Policy Gradient methods. It specifically covers Actor-Critic architectures for continuous and discrete action spaces, alongside Proximal Policy Optimization and Deep Deterministic Policy Gradients. The framewor

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

ART is a platform for agentic training, providing a reinforcement learning framework, training environment, and compute orchestrator. It enables the improvement of multi-step agent reasoning and tool usage through group relative policy optimization and a judge-based reward modeling system. The project features tools for model distillation to transfer capabilities from large teacher models to smaller architectures, as well as a system for capturing execution trajectories to generate synthetic training data. It supports specialized training workflows including supervised fine-tuning for baselin

This project is a collection of reinforcement learning implementations and educational materials written in Python. It provides neural network architectures for solving control tasks through deep reinforcement learning, spanning value-based and policy-gradient methods. The repository includes a library of evolutionary strategies and genetic algorithms as alternatives to gradient-based learning. It also features a model-based system for predicting future environment states and rewards to enable internal simulation and offline planning. The codebase covers a wide range of capabilities, includi

This is a PyTorch-based toolkit for training reinforcement learning agents, providing implementations of standard and hierarchical deep RL algorithms. It is designed as a library for deep reinforcement learning research and experimentation, supporting both discrete and continuous control tasks through a collection of algorithm implementations. The project distinguishes itself by offering a hierarchical reinforcement learning framework that decomposes complex long-horizon tasks into manageable sub-goals using meta-controllers and lower-level policies. It also includes a Hindsight Experience Re

This is a PyTorch reinforcement learning library designed for training agents in simulation environments. It provides a collection of deep reinforcement learning algorithms focusing on policy gradient methods and trust-region optimization. The library implements a suite of policy gradient algorithms, including A2C and PPO, alongside a framework for imitation learning using Generative Adversarial Imitation Learning. It specifically features a scalable implementation of the ACKTR algorithm, utilizing Kronecker-factored approximations to enable efficient trust-region optimization. The codebase

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

This project is a comprehensive collection of practical code examples and implementation libraries for machine learning. It provides a wide array of reference materials for building supervised, unsupervised, and reinforcement learning algorithms. The repository serves as a multi-domain resource, featuring specific implementation suites for financial AI, Bayesian statistical modeling, and deep learning architectures. It includes a framework for training intelligent agents using policy gradients and actor-critic models, as well as practical guides for fine-tuning transformers and utilizing larg

Open-r1 is a framework designed for the large-scale training, distillation, and optimization of language models focused on complex reasoning and programming tasks. It provides a comprehensive suite of tools for managing distributed training jobs across multi-node clusters, enabling the development of high-performance models through reinforcement learning and supervised fine-tuning. The project distinguishes itself by integrating secure, containerized code execution environments directly into the training and evaluation lifecycle. By allowing models to run and verify code snippets against test

Video-Pre-Training is a machine learning framework designed for training autonomous agents to perform complex tasks by observing and mimicking human behavior from video recordings. It provides a comprehensive toolkit for imitation learning and reinforcement learning research, enabling the development of agents that can replicate human actions within simulated digital environments. The framework distinguishes itself through its ability to process large-scale, unlabeled video datasets to bootstrap agent capabilities. It utilizes inverse dynamics modeling to infer control inputs from frame trans

EasyR1 is a distributed model training system and reinforcement learning framework for large language and vision-language models. It functions as a multimodal trainer and an implementation of a Proximal Policy Optimization pipeline designed to refine the reasoning and perception capabilities of models that process both text and images. The system specializes in distributing reinforcement learning workloads across multiple compute nodes to manage high memory requirements. It optimizes hardware utilization through padding-free training and fine-tuning to fit large models onto available graphics