PPGuide: Steering Diffusion Policies with Performance Predictive Guidance

• URL: http://arxiv.org/abs/2603.10980v1
• Date: Wed, 11 Mar 2026 17:10:16 GMT
• Title: PPGuide: Steering Diffusion Policies with Performance Predictive Guidance
• Abstract summary: PPGuide steers a pre-trained diffusion policy away from failure modes at inference time.<n>It uses attention-based multiple instance learning to automatically estimate which observation-action chunks from the policy's rollouts are relevant to success or failure.<n>We validated our proposed PPGuide across a diverse set of tasks from the Robomimic and MimicGen benchmarks.
• Score: 28.698103923760172
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion policies have shown to be very efficient at learning complex, multi-modal behaviors for robotic manipulation. However, errors in generated action sequences can compound over time which can potentially lead to failure. Some approaches mitigate this by augmenting datasets with expert demonstrations or learning predictive world models which might be computationally expensive. We introduce Performance Predictive Guidance (PPGuide), a lightweight, classifier-based framework that steers a pre-trained diffusion policy away from failure modes at inference time. PPGuide makes use of a novel self-supervised process: it uses attention-based multiple instance learning to automatically estimate which observation-action chunks from the policy's rollouts are relevant to success or failure. We then train a performance predictor on this self-labeled data. During inference, this predictor provides a real-time gradient to guide the policy toward more robust actions. We validated our proposed PPGuide across a diverse set of tasks from the Robomimic and MimicGen benchmarks, demonstrating consistent improvements in performance.

Related papers

• Large Discrete Policy: Advancing Explicit Behavior Modeling with Stochastic Iterative Scoring [77.17706435067372]
  Large Policy (LDiP) is a fully discrete behavior modeling framework that selects actions from a large vocabulary of physically plausible candidates.<n>Rather than perturbing actions, LDiP improves expressivity through iterative scoring.<n>Across end-to-end planning, closed-loop driving, robotic manipulation, and vision-language-action settings, LDiP consistently outperforms strong discrete and continuous baselines.
  arXiv  Detail & Related papers  (2026-09-07T05:12:52Z)
• LAFP: Preserving Latent Action Structure in Latent Policy Learning via Flow Matching [15.922360971421654]
  We propose Latent Action Flow Policy (LAFP) for scalable latent policy learning.<n>LAFP consistently outperforms prior methods on downstream imitation learning tasks.<n>LAFP incurs less than 1x additional inference overhead.
  arXiv  Detail & Related papers  (2026-06-09T07:49:49Z)
• Set-Supervised Diffusion Policy: Learning Action-Chunking Diffusion through Corrections [25.961145214027255]
  Diffusion policies provide paired supervision in the form of the robot's undesired actions and the human teacher's corrective actions.<n>We propose Set-Supervised Diffusion Policy (SDP), a novel learning framework that utilizes contrastive action-chunk data to train diffusion policies from human corrections.<n>SDP consistently improves policy performance, with particularly strong gains in robustness to noisy data.
  arXiv  Detail & Related papers  (2026-06-01T08:14:38Z)
• TapSampling: Inference-Time Sampling with a Task-Progress-Understanding Verifier for Robotic Manipulation [61.35569005726248]
  Existing embodied control research demonstrates remarkable performance improvements by scaling training data and model size.<n>Non-deterministic generative models, such as diffusion and autoregressive models, have been widely adopted in the field of embodied control.<n>We propose textbfTapSampling, a plug-and-play framework for inference-time sampling.
  arXiv  Detail & Related papers  (2026-05-25T08:03:31Z)
• Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach [78.4812458793128]
  We propose textbfTACO, a test-time-scaling framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks.<n>Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits.
  arXiv  Detail & Related papers  (2025-12-02T14:42:54Z)
• Model-Based Policy Adaptation for Closed-Loop End-to-End Autonomous Driving [54.46325690390831]
  We propose Model-based Policy Adaptation (MPA), a general framework that enhances the robustness and safety of pretrained E2E driving agents during deployment.<n>MPA first generates diverse counterfactual trajectories using a geometry-consistent simulation engine.<n>MPA trains a diffusion-based policy adapter to refine the base policy's predictions and a multi-step Q value model to evaluate long-term outcomes.
  arXiv  Detail & Related papers  (2025-11-26T17:01:41Z)
• SeFA-Policy: Fast and Accurate Visuomotor Policy Learning with Selective Flow Alignment [7.446137164545049]
  Selective Flow Alignment (SeFA) is an efficient and accurate visuomotor policy learning framework.<n>SeFA resolves this challenge by a selective flow alignment strategy.<n>It achieves superior accuracy and robustness while reducing inference latency by over 98%.
  arXiv  Detail & Related papers  (2025-11-11T18:59:39Z)
• Failure Prediction at Runtime for Generative Robot Policies [6.375597233389154]
  Early failure prediction during runtime is essential for deploying robots in human-centered and safety-critical environments.<n>We propose FIPER, a framework for failure prediction for generative robot policies that does not require failure data.<n>Our results demonstrate that FIPER better distinguishes actual failures from benign OOD situations and predicts failures more accurately and earlier than existing methods.
  arXiv  Detail & Related papers  (2025-10-10T15:09:27Z)
• CUPID: Curating Data your Robot Loves with Influence Functions [29.79350259314518]
  CUPID is a robot data curation method based on a novel influence function-theoretic formulation for imitation learning policies.<n>We use CUPID to curate data by 1) filtering out training demonstrations that harm policy performance and 2) subselecting newly collected trajectories that will most improve the policy.
  arXiv  Detail & Related papers  (2025-06-23T20:49:34Z)
• Dense Policy: Bidirectional Autoregressive Learning of Actions [51.60428100831717]
  This paper introduces a bidirectionally expanded learning approach, termed Dense Policy, to establish a new paradigm for autoregressive policies in action prediction.<n>It employs a lightweight encoder-only architecture to iteratively unfold the action sequence from an initial single frame into the target sequence in a coarse-to-fine manner.<n>Experiments validate that our dense policy has superior autoregressive learning capabilities and can surpass existing holistic generative policies.
  arXiv  Detail & Related papers  (2025-03-17T14:28:08Z)
• Inference-Time Policy Steering through Human Interactions [54.02655062969934]
  During inference, humans are often removed from the policy execution loop.<n>We propose an Inference-Time Policy Steering framework that leverages human interactions to bias the generative sampling process.<n>Our proposed sampling strategy achieves the best trade-off between alignment and distribution shift.
  arXiv  Detail & Related papers  (2024-11-25T18:03:50Z)
• InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance [56.184255657175335]
  We develop textbfInferAligner, a novel inference-time alignment method that utilizes cross-model guidance for harmlessness alignment. Experimental results show that our method can be very effectively applied to domain-specific models in finance, medicine, and mathematics. It significantly diminishes the Attack Success Rate (ASR) of both harmful instructions and jailbreak attacks, while maintaining almost unchanged performance in downstream tasks.
  arXiv  Detail & Related papers  (2024-01-20T10:41:03Z)
• Stochastic Action Prediction for Imitation Learning [1.6385815610837169]
  Imitation learning is a data-driven approach to acquiring skills that relies on expert demonstrations to learn a policy that maps observations to actions. We demonstrate inherentity in demonstrations collected for tasks including line following with a remote-controlled car. We find that accounting for adversariality in the expert data leads to substantial improvement in the success rate of task completion.
  arXiv  Detail & Related papers  (2020-12-26T08:02:33Z)
• Hierarchical Variational Imitation Learning of Control Programs [131.7671843857375]
  We propose a variational inference method for imitation learning of a control policy represented by parametrized hierarchical procedures (PHP) Our method discovers the hierarchical structure in a dataset of observation-action traces of teacher demonstrations, by learning an approximate posterior distribution over the latent sequence of procedure calls and terminations. We demonstrate a novel benefit of variational inference in the context of hierarchical imitation learning: in decomposing the policy into simpler procedures, inference can leverage acausal information that is unused by other methods.
  arXiv  Detail & Related papers  (2019-12-29T08:57:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.