Skip to main content
Back to top
Ctrl
+
K
AI
Ask AI
RLinf
Ctrl
+
K
Choose version
EN
English
ä¸ć–‡
GitHub
Get Started
Requirements
Installation
Quick Start
Cheat Sheet
Examples
Simulators
ManiSkill
LIBERO
Behavior
MetaWorld
IsaacLab
CALVIN
RoboCasa
RoboTwin
RoboVerse
Franka-Sim
EmbodiChain
PolaRiS
GSEnv
Genesis
Robots
Franka
Reward Model
ZED + Robotiq
GELLO
VR / PICO
Dual-Arm
Dexterous Hand
Pi0 SFT
HG-DAgger
GimArm
XSquare Turtle2
DOS-W1
Models
MLP
π₀ / π₀.₅
GR00T
Lingbot-VLA
Dexbotic
StarVLA
ABot-M0
OpenSora
Wan
SFT
OpenPI
DreamZero
VLM
Algorithms
SAC-Flow
DSRL
DAgger
RECAP
Co-Training
IQL (D4RL)
Agents
WideSeek-R1
Tool Setup
WideSeek-R1 Training
WideSeek-R1 Evaluation
AgentLightning
Coding Online RL
Search-R1
rStar2
Math GRPO
Math PPO
Qwen3 VL GRPO
Systems
FUSCO High-Performance MoE Communication Library
Evaluation
Get Started
Overview
Installation
Quick Tour
Benchmark Guides
Real-World Evaluation
BEHAVIOR-1K Evaluation
LIBERO Evaluation
ManiSkill OOD Evaluation
PolaRiS Evaluation
RoboTwin Evaluation
Reference
Configuration Reference
CLI Reference
Supported Models
Logs and Results
Guides
Configure
Basic Configuration
Embodied Configuration
Agentic Configuration
Logging
Launch & Scale
Multi-Node Training
Heterogeneous Clusters
Cloud-Edge Collaboration
Real-World Robots
Data & Checkpoints
Data Collection
Checkpoint Conversion
Resume Training
Performance
Auto Placement
Dynamic Scheduling
Profiling
5D Parallelism
LoRA
Env Decoupled Mode
Hardware Backends
AMD ROCm
Ascend CANN
Agent Workflows
Agentic Guides
Rollout Engines
SGLang Server & Router
InferenceHTTPClient
SGLang Version Switching
Concepts
Execution Model
RLinf Execution Flow
M2Flow Programming Flow
Worker and WorkerGroup
Cluster
Channel
Collective Communication
Scheduling Model
Placement
Execution Modes
Replay Buffer
Reference
API
Worker Interface
Placement Interface
Cluster Interface
Channel Interface
Actor Interface
Rollout Interface
Environment Interface
Data Interface
Embodied Data Interface
Replay Buffer
Algorithms
PPO
GRPO
DAPO
Reinforce++
SAC
CrossQ
RLPD
IQL
Async PPO
Configuration
Training Configuration
Training Metrics
Extending
Extending Overview
New Environment
New Model with FSDP
New Model with Megatron
New SFT Model
Advanced Integrations
Megatron-Bridge
Weight Synchronization
Reward Model Workflow
Resources
Why RLinf
Blog
Comparison with VeRL
A First Look at the “Last Mile” of Agent Deployment: Cursor Online Reinforcement Learning
Accelerating the “ImageNet Moment” of Embodied AI: RLinf Brings a 25× System Optimization to BEHAVIOR
Publications
RLinf-USER: Unified System for Real-world Online Policy Learning
RLinf-VLA: A Unified and Efficient Framework for VLA+RL Training
Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models
RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformation
Ď€RL: Online RL Fine-tuning for Flow-based Vision-Language-Action Models
WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL
WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning
v0.1 & v0.2 Release Notes
v0.3 Release Notes
FAQ
Search
Error
Please activate JavaScript to enable the search functionality.
Ctrl
+
K
