Search Results for "reinforcement learning" - Page 3
Sort By:
Showing 172 open source projects for "reinforcement learning"
View related business solutions-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
$300 in Free Credit Towards Top Cloud ServicesStart your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.
-
1
robosuite
A Modular Simulation Framework and Benchmark for Robot Learning
Robosuite is a modular and extensible simulation framework for robotic manipulation tasks, built on top of MuJoCo. Developed by the ARISE Initiative, Robosuite offers a set of standardized benchmarks and customizable environments designed to advance research in robotic manipulation, control, and imitation learning. It emphasizes realistic simulations and ease of use for both single-task and multi-task learning. -
2
verl-agent
Designed for training LLM/VLM agents via RL
verl-agent is an open-source reinforcement learning framework designed to train large language model agents and vision-language model agents for complex interactive environments. Built as an extension of the veRL reinforcement learning infrastructure, the project focuses on enabling scalable training for agents that perform multi-step reasoning and decision-making tasks. -
3
Humanoid-Gym
Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real
Humanoid-Gym is a reinforcement learning framework designed to train locomotion and control policies for humanoid robots using high-performance simulation environments. The system is built on top of NVIDIA Isaac Gym, which allows large-scale parallel simulation of robotic environments directly on GPU hardware. Its primary goal is to enable efficient training of humanoid robots in simulation while enabling policies to transfer effectively to real-world hardware without additional training. ... -
4
Diffusion for World Modeling
Learning agent trained in a diffusion world model
Diffusion for World Modeling is an experimental reinforcement learning system that trains intelligent agents inside a simulated environment generated by a diffusion-based world model. The project introduces the idea of using diffusion models, commonly used for image generation, to simulate the dynamics of an environment and predict future states based on previous observations and actions. -
Auth0 B2B Essentials: SSO, MFA, and RBAC Built InAuth0's B2B Essentials plan gives you everything you need to ship secure multi-tenant apps. Unlimited orgs, enterprise SSO, RBAC, audit log streaming, and higher auth and API limits included. Add on M2M tokens, enterprise MFA, or additional SSO connections as you scale.
-
5
RLHF-Reward-Modeling
Recipes to train reward model for RLHF
RLHF-Reward-Modeling is an open-source research framework focused on training reward models used in reinforcement learning from human feedback for large language models. In RLHF pipelines, reward models are responsible for evaluating generated responses and assigning scores that guide the model toward outputs that better match human preferences. The repository provides training recipes and implementations for building reward and preference models using modern machine learning frameworks. ... -
6
CUDA Agent
Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
CUDA Agent is a research-driven agentic reinforcement learning system designed to automatically generate and optimize high-performance CUDA kernels for GPU workloads. The project addresses the long-standing challenge that efficient CUDA programming typically requires deep hardware expertise by training an autonomous coding agent capable of iterative improvement through execution feedback. -
7
ReCall
Learning to Reason with Search for LLMs via Reinforcement Learning
...Instead of relying purely on static knowledge stored inside the model, ReCall allows the language model to dynamically decide when it should retrieve information or invoke external capabilities during the reasoning process. The framework uses reinforcement learning to train models to perform these tool calls effectively while solving multi-step reasoning tasks. -
8
Reco-papers
Classic papers and resources on recommendation
Reco-papers is a curated repository that collects influential research papers, technical resources, and industry materials related to recommender systems and recommendation algorithms. The project organizes a large body of literature into thematic sections such as classic recommender systems, exploration-exploitation strategies, deep learning–based recommendation models, and cold-start mitigation techniques. It serves as a reference library for researchers and engineers who want to explore foundational and cutting-edge work in recommendation technologies. The repository includes papers from academic institutions and industry organizations and groups them according to topics such as retrieval and reranking, reinforcement learning in recommendation, and feature engineering infrastructure. ... -
9
highway-env
A minimalist environment for decision-making in autonomous driving
HighwayEnv is an OpenAI Gym-compatible environment focused on autonomous driving scenarios. It provides flexible simulations for testing decision-making algorithms in highway, intersection, and merging traffic situations. -
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
10
Sapiens
High-resolution models for human tasks
...It includes simulation environments, datasets, and benchmarks for testing grounded understanding, imitation learning, and decision-making. The system’s modular pipeline supports both imitation-based and reinforcement-based training strategies, allowing flexible experimentation with different embodiments and tasks. -
11
Tongyi DeepResearch
Tongyi Deep Research, the Leading Open-source Deep Research Agent
...The model is about 30.5 billion parameters in size, though at any given token only ~3.3B parameters are active. It uses a mix of synthetic data generation, fine-tuning and reinforcement learning; supports benchmarks like web search, document understanding, question answering, “agentic” tasks; provides inference tools, evaluation scripts, and “web agent” style interfaces. The aim is to enable more autonomous, agentic models that can perform sustained knowledge gathering, reasoning, and synthesis across multiple modalities (web, files, etc.). -
12
R1-V
Witness the aha moment of VLM with less than $3
R1-V is an initiative aimed at enhancing the generalization capabilities of Vision-Language Models (VLMs) through Reinforcement Learning in Visual Reasoning (RLVR). The project focuses on building a comprehensive framework that emphasizes algorithm enhancement, efficiency optimization, and task diversity to achieve general vision-language intelligence and visual/GUI agents. The team's long-term goal is to contribute impactful open-source research in this domain. -
13
MetaClaw
Just talk to your agent
MetaClaw is an AI or agent-oriented system that appears to focus on advanced control, coordination, or training of autonomous agents, potentially within reinforcement learning or tool-using environments. The project likely emphasizes meta-level reasoning, where agents are not only executing tasks but also adapting their strategies based on feedback and performance signals. It may incorporate mechanisms for learning from interactions, improving decision-making over time, and generalizing across different domains. ... -
14
PKU Beaver
Constrained Value Alignment via Safe Reinforcement Learning
PKU Beaver is an open-source research project focused on improving the safety alignment of large language models through reinforcement learning from human feedback under explicit safety constraints. The framework introduces techniques that separate helpfulness and harmlessness signals during training, allowing models to optimize for useful responses while minimizing harmful behavior. To support this process, the project provides datasets containing human-labeled examples that encode both performance preferences and safety constraints across multiple dimensions. ... -
15
Ring
Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI
...Its design emphasizes reasoning, efficiency, and modular expert activation. In its “flash” variant (Ring-flash-2.0), it optimizes inference by activating only a subset of experts. It applies reinforcement learning/reasoning optimization techniques. Its architectures and training approaches are tuned to enable efficient and capable reasoning performance. Reasoning-optimized model with reinforcement learning enhancements. Efficient architecture and memory design for large-scale reasoning. If you are located in mainland China, we also provide the model on ModelScope.cn to speed up the download process. -
16
Youtu-Agent
A simple yet powerful agent framework that delivers with models
...The framework supports automated generation of agent components, enabling the system to synthesize prompts, tool interfaces, and workflow configurations automatically. Youtu-Agent also incorporates hybrid learning strategies that combine experience accumulation with reinforcement learning to improve agent performance over time. These learning mechanisms allow agents to refine their reasoning, coding, and search capabilities as they interact with environments and tasks. -
17
LiteMultiAgent
The Library for LLM-based multi-agent applications
LiteMultiAgent is a lightweight and extensible multi-agent reinforcement learning (MARL) platform designed for rapid experimentation. It allows researchers to design and test coordination, competition, and collaboration scenarios in simulated environments. -
18
Minigrid
Simple and easily configurable grid world environments
Minigrid is a lightweight, minimalistic grid-world environment library for reinforcement learning (RL) research. It provides a suite of simple 2D grid-based tasks (e.g., navigating mazes, unlocking doors, carrying keys) where an agent moves in discrete steps and interacts with objects. The design emphasizes speed (agents can run thousands of steps per second), low dependency overhead, and high customizability — making it easy to define new maps, new tasks, or wrappers. ... -
19
PilottAI
Python framework for building scalable multi-agent systems
pilottai is an AI-based autonomous drone navigation system utilizing reinforcement learning for real-time decision-making. It is designed for simulating and training drones to fly safely through dynamic environments using AI-based controllers. -
20
AgentEvolver
Towards Efficient Self-Evolving Agent System
...The system focuses on improving the efficiency and scalability of training autonomous agents by allowing them to generate tasks, explore environments, and refine strategies without heavy reliance on manually curated datasets. Its architecture combines reinforcement learning with LLM-driven reasoning mechanisms to guide exploration and learning. The framework introduces several key mechanisms, including self-questioning to create new learning tasks, self-navigating to improve exploration through experience reuse, and self-attributing to assign rewards based on the usefulness of actions. ... -
21
Agent Behavior Monitoring
The open source post-building layer for agents
...Developers can use the framework to observe agent actions in both online production environments and offline evaluation settings, making it useful for debugging and performance analysis. Judgeval transforms agent interaction trajectories into structured evaluation datasets that can be used for reinforcement learning, supervised fine-tuning, or other forms of post-training improvement. The framework includes tools that analyze agent behavior patterns and group interaction trajectories by behavior type or topic, allowing researchers to detect weaknesses or unexpected behaviors. -
22
Unsloth Studio
Unified web UI for training and running open models locally
...Built on top of the Unsloth framework, it focuses on high-performance training with reduced VRAM usage and faster speeds compared to traditional methods. The platform supports fine-tuning, pretraining, and reinforcement learning workflows, making it suitable for both experimentation and production use. Users can interact with models through chat, upload files like PDFs or images, and execute code within the environment to improve outputs. By combining powerful optimization techniques with an intuitive UI, Unsloth Studio simplifies the process of building and customizing AI models locally. -
23
Pearl
A Production-ready Reinforcement Learning AI Agent Library
Pearl is a production-ready reinforcement learning and contextual bandit agent library built for real-world sequential decision making. It is organized around modular components—policy learners, replay buffers, exploration strategies, safety modules, and history summarizers—that snap together to form reliable agents with clear boundaries and strong defaults. The library implements classic and modern algorithms across two regimes: contextual bandits (e.g., LinUCB, LinTS, SquareCB, neural bandits) and fully sequential RL (e.g., DQN, PPO-style policy optimization), with attention to practical concerns like nonstationarity and dynamic action spaces. ... -
24
MiniOneRec
Minimal reproduction of OneRec
...The framework provides an end-to-end pipeline for building generative recommender systems, including semantic identifier construction, supervised fine-tuning, and reinforcement learning-based optimization. Semantic IDs are created using techniques such as quantized variational autoencoders to convert item features into token sequences that can be modeled by transformer architectures. Developers can train and evaluate recommendation models using different backbone language models while benefiting from the generative framework’s parameter efficiency and scalability. -
25
AgentScope
Build and run agents you can see, understand and trust
...With built-in support for ReAct agents, memory, planning, human-in-the-loop control, and real-time voice interaction, developers can create powerful agents in minutes. AgentScope integrates seamlessly with tools, long-term memory systems, MCP, A2A (Agent-to-Agent) protocols, and observability frameworks. It also supports reinforcement learning workflows for tuning agents and improving performance across complex tasks. Deployable locally, serverless in the cloud, or on Kubernetes with OpenTelemetry support, AgentScope is built for both experimentation and production environments.
