# Policy Gradient Guidance Enables Test Time Control

arXiv: https://arxiv.org/abs/2510.02148 · HTML: https://mlsanity.com/paper/2510.02148/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 13 of its 18 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)
- Deep reinforcement learning methods / [RL theory and sample complexity](https://mlsanity.com/deeprl/rl-theory-and-sample-complexity/)

## Builds on (most cited first, 13 of 13)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Is Conditional Generative Modeling all you need for Decision-Making?](https://mlsanity.com/paper/2211.15657/) (2022)
- [Diffusion-based Generation, Optimization, and Planning in 3D Scenes](https://mlsanity.com/paper/2301.06015/) (2023)
- [Diffusion Guidance Is a Controllable Policy Improvement Operator](https://mlsanity.com/paper/2505.23458/) (2025)

## Built on by (most cited first, 1 of 1)

- [Policy Gradient Steering: Interventions from Behavioral Objectives](https://mlsanity.com/paper/2607.27574/) (2026)

## Abstract (arXiv)

We introduce Policy Gradient Guidance (PGG), a simple extension of classifier-free guidance from diffusion models to classical policy gradient methods. PGG augments the policy gradient with an unconditional branch and interpolates conditional and unconditional branches, yielding a test-time control knob that modulates behavior without retraining. We provide a theoretical derivation showing that the additional normalization term vanishes under advantage estimation, leading to a clean guided policy gradient update. Empirically, we evaluate PGG on discrete and continuous control benchmarks. We find that conditioning dropout-central to diffusion guidance-offers gains in simple discrete tasks and low sample regimes, but dropout destabilizes continuous control. Training with modestly larger guidance (γ>1) consistently improves stability, sample efficiency, and controllability. Our results show that guidance, previously confined to diffusion policies, can be adapted to standard on-policy methods, opening new directions for controllable online reinforcement learning.