Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning
cs.LG, cs.AI
Submitted: 2026-06-09
Updated: 2026-10-27
Code: https://github.com/zhouzypaul/qgf
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling
- One-Step Flow Policy Mirror Descent
- Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning
- Scaling Offline RL via Efficient and Expressive Shortcut Models
- Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning
- Diffusion Guidance Is a Controllable Policy Improvement Operator
- Extreme Q-Learning: MaxEnt RL without Entropy
- IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies
- DiffCPS: Diffusion Model based Constrained Policy Search for Offline Reinforcement Learning
- Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance
- Flow-Based Single-Step Completion for Efficient and Expressive Policy Learning
- Offline Reinforcement Learning with Implicit Q-Learning
- Reward-Conditioned Policies
- Q-learning with Adjoint Matching
- Decoupled Q-Chunking
- Reinforcement Learning with Action Chunking
- Random feedback weights support learning in deep neural networks
- Continuous control with deep reinforcement learning
- Flow Matching for Generative Modeling
- Flow-Based Policy for Online Reinforcement Learning
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis