9 repository-uri
Frameworks that provide the structural support and abstractions for implementing reinforcement learning agents.
Distinct from Algorithm Implementations: Focuses on the framework for implementation rather than a static collection of ready-made algorithms.
Explore 9 awesome GitHub repositories matching artificial intelligence & ml · RL Agent Implementation Frameworks. Refine with filters or upvote what's useful.
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
Ships frameworks to implement agents for both discrete and continuous control tasks.
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
Provides a framework for creating standalone, single-file implementations of RL algorithms to simplify prototyping and research.
rllm is an asynchronous reinforcement learning framework for training language agents. It provides a unified pipeline that runs the same agent code for both evaluation and training, automatically capturing traces for gradient computation. The framework supports distributed reinforcement learning across multiple GPUs and nodes using pluggable backends, and executes agents in isolated sandboxes—either locally or in the cloud—for safe and scalable rollout collection. It trains agents built with LangGraph, SmolAgents, OpenAI Agents SDK, or custom frameworks without requiring core logic changes. T
Core identity: an async reinforcement learning framework specifically for training language agents.
keras-rl este o bibliotecă de reinforcement learning care permite antrenarea agenților neuronali folosind Keras. Servește drept framework pentru implementarea agenților de deep reinforcement learning care interacționează cu medii simulate pentru a descoperi comportamente optime și a maximiza recompensele cumulative. Biblioteca oferă un sistem pentru configurarea, antrenarea și gestionarea agenților de rețele neuronale. Gestionează bucla de interacțiune dintre agenți și medii, permițând modelelor să învețe prin experiență directă și optimizare bazată pe gradient. Framework-ul include capabilități pentru gestionarea ponderilor modelelor, permițând utilizatorilor să salveze și să restaureze stările învățate ale agenților antrenați pentru a păstra progresul sau a-i implementa pentru evaluare.
Provides the structural support and abstractions needed to implement reinforcement learning agents.
Acest proiect este un curriculum de deep reinforcement learning care oferă materiale educaționale și exerciții de implementare pentru stăpânirea agenților bazați pe rețele neuronale. Acesta servește drept framework pentru construirea versiunilor de referință ale metodelor bazate pe valoare și pe politică pentru a rezolva probleme de decizie secvențială. Proiectul oferă implementări specifice pentru simulări de control continuu și reinforcement learning multi-agent, unde agenții sunt antrenați să coopereze sau să concureze în medii partajate. Include un framework de gradient de politică pentru optimizarea comportamentului agentului prin metode precum REINFORCE. Capabilitățile acoperă o gamă largă de algoritmi de optimizare, inclusiv deep Q-learning, gradienți de politică deterministă și programare dinamică pentru modelarea proceselor de decizie Markov. Sistemul suportă diverse domenii de antrenament, cum ar fi navigația robotică, automatizarea tranzacțiilor financiare și simulările bazate pe fizică. Materialele sunt livrate sub forma unei serii de Jupyter Notebooks.
Provides a structural framework for building reference versions of value-based and policy-based reinforcement learning agents.
Verifiers este un framework de mediu de reinforcement learning și un toolkit de evaluare conceput pentru a antrena și evalua modele de limbaj mari. Oferă un sistem standardizat pentru construirea mediilor de simulare, gestionarea harness-urilor de antrenament și urmărirea traiectoriilor agenților prin interacțiuni multi-turn. Proiectul include un manager de traiectorii de agenți dedicat pentru a gestiona rollout-urile ramificate și secvențele de token-uri, alături de un toolkit de evaluare care testează output-urile modelului față de rubrici de recompensă și seturi de date definite. Include capabilități pentru reward engineering și capacitatea de a împacheta module de mediu pentru partajare distribuită și execuție remote. Framework-ul acoperă o gamă largă de domenii operaționale, inclusiv colectarea automată de metrici, analiza performanței bazată pe ablație și integrarea harness-urilor de model cu fluxuri de lucru de reinforcement learning pentru a optimiza comportamentul agentului.
Implements a framework for setting up task datasets, model harnesses, and reward rubrics for LLM evaluation and training.
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
Hosts a model and improves it from prior conversations using asynchronous RL that does not interfere with API serving.
Acme is a reinforcement learning framework and execution engine designed for developing and benchmarking learning algorithms. It provides a library of modular components and reference implementations used to construct agents and establish performance baselines. The system enables the scaling of agent architectures from single-stream execution to large distributed environments. This allows for the transition from initial prototyping to distributed execution for training and evaluation. The framework covers reinforcement learning development and agent architecture prototyping, providing the bu
Provides the structural support and modular building blocks necessary for implementing RL agents.
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
Provides a comprehensive collection of pretrained reinforcement learning agents and training scripts built on Stable Baselines3.