Projects sharing features with Acme

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

This project is a collection of pretrained reinforcement learning agents and training scripts built on Stable Baselines3 and Gymnasium. It provides a framework for training agents to solve specific tasks, managing experiment reproducibility, and deploying pretrained models. The system includes a specialized benchmarking suite and optimization tools for tuning agent settings. It utilizes automated search spaces and distributed trials to maximize performance, while employing bootstrap sampling to generate statistically robust performance metrics and confidence intervals. Broad capabilities cov

Tianshou is a reinforcement learning framework designed for developing and testing agents. It provides a system for implementing custom agents by defining policies and parameter update rules to optimize agent behavior. The framework decouples neural network architectures from update logic through policy-based abstractions and separates data pre-processing from gradient updates. It utilizes a collector-driven pipeline to stream experience from environments into structured memory buffers for sampled learning. The system supports vectorized environment execution to run multiple parallel instanc

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

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 an educational resource designed to teach the mathematical foundations and core algorithms of reinforcement learning. It provides a structured academic curriculum that combines textbooks, lecture materials, and practical code examples to guide learners through the principles of Markov decision processes and reinforcement learning theory. The repository distinguishes itself by integrating a grid-based simulation framework that allows users to test algorithms within custom environments. This environment supports the analysis of agent performance by rendering state values, polici

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

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

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

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

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

DeepMimic is a deep reinforcement learning framework and physics-based motion imitation tool designed to teach simulated characters and robots to reproduce human movements. It provides a pipeline for integrating motion capture data into physics simulations to train agents that can mimic complex physical skills. The system utilizes the PyBullet simulation environment to execute motion policies and visualize character interactions in real time. It includes a motion capture integration pipeline that imports and processes animation sequences to serve as reference targets for imitation learning ag

This project is a deep reinforcement learning curriculum providing educational materials and implementation exercises for mastering neural network-based agents. It serves as a framework for building reference versions of value-based and policy-based methods to solve sequential decision problems. The project provides specific implementations for continuous control simulations and multi-agent reinforcement learning, where agents are trained to cooperate or compete in shared environments. It includes a policy gradient framework for optimizing agent behavior through methods such as REINFORCE. Ca

This project is a machine learning implementation library featuring a collection of code examples that implement supervised, unsupervised, and reinforcement learning algorithms from scratch. It provides a comprehensive set of toolkits for core machine learning components, including a natural language processing toolkit, a reinforcement learning framework, and suites for data dimensionality reduction and pattern mining. The library includes specialized implementations for reinforcement learning, such as Q-Learning, Deep Q-Networks, and Actor-Critic agents. The natural language processing capab

TensorLayer is a backend-agnostic tensor library and deep learning framework designed for building neural network architectures. It provides a neural network abstraction layer that allows model logic to run across different deep learning engines using high-level layers and model components. The project serves as a deep reinforcement learning toolkit for implementing policy-based, value-based, and actor-critic agents. It includes specialized tools for managing experience replay and gradient-based policy optimization to handle both discrete and continuous action spaces. To support reinforcemen

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

IsaacGymEnvs is a GPU-accelerated physics sandbox and robotics policy training suite designed for reinforcement learning. It serves as a vectorized robotic simulator that runs thousands of parallel environments on GPUs to accelerate the training of neural networks. The project provides a sim-to-real transfer framework that utilizes domain randomization and physics variations to ensure policies trained in simulation are robust enough for deployment on real hardware. It distinguishes itself through a high-performance architecture that uses tensor-based state management to handle observations an

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

This project is a game AI training framework designed to develop and monitor reinforcement learning agents within a legacy game environment. It functions as a training and monitoring system that optimizes autonomous agents to complete game objectives through exploration and reward-based learning. The framework includes tools for game memory mapping and real-time trajectory visualization. These capabilities translate raw game memory addresses into visual coordinates, allowing agent movements and session data to be streamed to a map for the analysis of navigation patterns and area exploration.

Minigo is a TensorFlow-based reinforcement learning engine designed to master the game of Go. It functions as a comprehensive system for training neural networks to predict board policies and game outcomes, utilizing a model trainer to generate self-play data and optimize weights. The project is distinguished by its ability to perform large-scale game simulations using Kubernetes to distribute worker nodes across CPU, GPU, and TPU hardware. It employs a Monte Carlo Tree Search implementation to identify optimal moves and supports specialized hardware acceleration, including inference on Edge

This project provides a comprehensive technical guide and framework for engineering large-scale machine learning systems. It covers the full lifecycle of model development, focusing on the infrastructure and computational principles required to build, train, and serve generative AI models across distributed GPU clusters. The repository distinguishes itself by offering deep-dive tutorials and implementation strategies for complex system challenges. It emphasizes high-performance architectural primitives, such as collective communication orchestration, distributed tensor sharding, and static gr

HRM is an automated reasoning engine and language framework designed to execute complex, multi-scale problem solving. It functions as a reinforcement learning agent that continuously updates internal knowledge representations to improve task performance based on incoming data streams. The system distinguishes itself through a hierarchical architecture that coordinates abstract, long-term planning with granular, low-level logic. By integrating evolutionary algorithms and reinforcement learning, the framework refines model parameters and weights over successive generations, ensuring that intern

This project is an educational platform and research toolkit designed to teach deep learning through a combination of mathematical theory, visual diagrams, and executable code. It provides a comprehensive environment for building, training, and evaluating neural networks, grounding complex concepts in interactive computational notebooks that allow for hands-on experimentation. The framework distinguishes itself by interleaving theoretical foundations—including linear algebra, calculus, and probability—with practical implementations across multiple industry-standard libraries. It supports flex

Trax is a deep learning framework and hardware-agnostic tensor engine designed for designing and training neural networks. It serves as a research tool providing high-level combinators for composing complex architectures, alongside a dedicated library for building transformer models and a toolkit for reinforcement learning. The framework is distinguished by its support for reversible and sparse transformer architectures, which reduce memory and computational overhead. It enables a single set of model instructions to execute across different hardware backends without changing the underlying co

This repository is a collection of implementation references and solved notebooks covering supervised, unsupervised, and reinforcement learning techniques. It provides practical guides for building predictive models, clustering algorithms, and autonomous agents. The project includes specific implementations for neural network architectures, such as multi-layer perceptrons for digit recognition, and recommender systems using collaborative and content-based filtering. It also features reinforcement learning systems that utilize deep Q-learning to optimize decision-making policies. The codebase

mctx is a framework for executing high-performance tree search and state simulations to generate policy targets for neural networks. It functions as a compiled search engine and neural dynamics simulator that predicts state transitions and rewards using learned representations. The project implements a vectorised tree search capable of running parallel search operations across input batches. It utilizes a policy target generator to convert search results into action weights used for training and refining neural network policies. The system covers reinforcement learning workflows by integrati

simpleRL-reason is a training framework designed to improve mathematical and logical deduction in large language models. It utilizes reinforcement learning and policy optimization to enhance the accuracy and transparency of step-by-step deduction chains. The project implements a pipeline that establishes baseline capabilities through supervised fine-tuning before applying reinforcement learning to maximize deductive accuracy. It features a reward modeling toolkit that calculates scalar feedback by comparing generated reasoning steps against verified mathematical ground truths. The framework