Flow-Based Policy Learning

Follow this topic Ask about this topic

Latest papers

37 papers10 papers in the last four weeks, up 233% on the four weeks before. 0.1% of all new papers.

Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies
Mar 16, 2026Mumuksh Tayal, Manan Tayal, Ravi PrakashFlow Matching Offline RL
Indian Institute of Science, India
Evaluating GFlowNet from partial episodes for stable and flexible policy-based training
Mar 1, 2026Puhua Niu, Shili Wu, Xiaoning QianGenerative Flow Networks Flow-Based Policy Learning
Texas A&M University, College Station, TX 77843, USA · Brookhaven National Laboratory, Upton, NY 11973, USA
Flow Actor-Critic for Offline Reinforcement Learning
Feb 20, 2026Jongseong Chae, Jongeui Park, Yongjae Shin +3Flow-Based Policy Learning Conservative RL
KAIST · UNIST
Flow Policy Gradients for Robot Control
Feb 2, 2026Brent Yi, Hongsuk Choi, Himanshu Gaurav Singh +9Robotic Control RL for Robotics
Amazon FAR · UC Berkeley · Stanford +2
DeFlow: Decoupling Behavior-Prior Modeling and Value Maximization for Offline Policy Extraction
Jan 15, 2026Zhancun Mu, Chi ZhangOffline RL Policy Learning
Peking University, Institute of Artificial Intelligence, China, Beijing.
Learning Robust Visuomotor Policies via Dynamics Alignment
Oct 31, 2025Dohyeok Lee, Jung Min Lee, Munkyung Kim +7Visuomotor Policy Learning Flow-Based Policy Learning
Department of Electrical and Computer Engineering, Seoul National University, Seoul 08826, Korea · Department of Statistics, Korea University, Seoul 02841, Korea
Normalizing Flows are Capable Models for Continuous Control
May 29, 2025Raj Ghugare, Benjamin EysenbachNormalizing Flows Reinforcement Learning
Department of Computer Science Princeton University

Mar 16, 2026J/K move · Enter open · S save

Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies

Mumuksh Tayal, Manan Tayal, Ravi Prakash

Indian Institute of Science, India

Flow Matching Offline RL Safe RL Flow-Based Policy Learning

Open paper AskPDF arXiv

Offline safe reinforcement learning (RL) seeks reward-maximizing policies from static datasets under strict safety constraints. Existing methods often rely on soft expected-cost objectives or iterative generative inference, which can be insufficient for safety-critical real-time control. We propose Safe Flow Q-Learning (SafeFQL), which extends FQL to safe offline RL by combining a Hamilton--Jacobi reachability-inspired safety value function with an efficient one-step flow policy. SafeFQL learns the safety value via a self-consistency Bellman recursion, trains a flow policy by behavioral cloning, and distills it into a one-step actor for reward-maximizing safe action selection without rejection sampling at deployment. Empirically, SafeFQL trades modestly higher offline training cost for substantially lower inference latency than diffusion-style safe generative baselines, which is advantageous for real-time safety-critical deployment. Across boat navigation, and Safety Gymnasium MuJoCo tasks, SafeFQL matches or exceeds prior offline safe RL performance while substantially reducing constraint violations.