Uncertainty-Guided Sparse Refinement for Action Chunking Transformer Policies

• URL: http://arxiv.org/abs/2609.15840v1
• Date: Mon, 14 Sep 2026 16:37:35 GMT
• Title: Uncertainty-Guided Sparse Refinement for Action Chunking Transformer Policies
• Abstract summary: Recent action-chunking methods have shown promising performance by predicting temporally extended action sequences.<n>We propose Uncertainty-Guided Refinement (UGR), a sparse refinement framework for chunk-based visuomotor policies.
• Score: 10.02061062596699
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning chunk-based visuomotor policies for long-horizon robot manipulation remains challenging. Recent action-chunking methods have shown promising performance by predicting temporally extended action sequences. However, their failures are often dominated by prediction errors at a small number of critical timesteps rather than uniformly poor predictions across the entire action chunk, making uniform refinement inefficient and insufficiently targeted. To address this bottleneck, we propose Uncertainty-Guided Refinement (UGR), a sparse refinement framework for chunk-based visuomotor policies. Specifically, UGR follows a coarse-to-refine design: it first predicts a full action chunk, estimates per-step temporal uncertainty from the coarse hidden states, and applies residual correction only to the most uncertain timesteps selected by a binary mask. The uncertainty branch is decoupled from the coarse action predictor, enabling clean attribution of the refinement gains to uncertainty-guided correction rather than additional predictor capacity. Extensive experiments on five dual-arm manipulation tasks from the RoboTwin benchmark show that UGR achieves the best success rate on four tasks, improves over the ACT baseline by up to 13% absolute, and outperforms both full-chunk and position-agnostic block refinement in ablation studies.

Related papers

• Beyond Optimal Rates in Stochastic Optimization: Trajectory-Adaptive Stopping Rules [42.38093055717409]
  We develop new confidence-sequence techniques and a general time-uniform empirical Bernstein inequality for adapted processes.<n>We show that the resulting stopping rules can require several orders of fewer than natural gradient horizons.
  arXiv  Detail & Related papers  (2026-08-26T09:02:46Z)
• PREFAIL: Identifying Precursors to Failures in Robotic Lift-and-Place Tasks to Improve Task Execution Performance [18.15066408206677]
  We propose a more effective approach to predicting precursors to failures (PREFAIL) by analyzing the relative motion of target objects with respect to the carrier.<n>Our experimental results demonstrate that PREFAIL substantially improves both the accuracy and timeliness of responses to failure precursors.
  arXiv  Detail & Related papers  (2026-07-18T18:25:58Z)
• PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models [50.232333672172395]
  Vision-Language-Action (VLA) models provide a unified paradigm for robotic manipulation, yet their real-world deployment is often bottlenecked by execution efficiency.<n>We propose textbfPolicyTrim, a reinforcement learning-based post-training framework that extends the reliable action chunk length and reduces redundant physical steps.<n>Our framework delivers up to a 5.83$times$ end-to-end deployment speedup without compromising task success rates.
  arXiv  Detail & Related papers  (2026-06-21T14:54:07Z)
• Shifting Uncertainty to Critical Moments: Towards Reliable Uncertainty Quantification for VLA Model [10.781664119473966]
  We propose a unified uncertainty quantification approach for predicting rollout success versus failure.<n>Our method substantially improves failure prediction accuracy and yields more reliable signals for failure detection.
  arXiv  Detail & Related papers  (2026-03-18T22:52:03Z)
• Seeing Farther and Smarter: Value-Guided Multi-Path Reflection for VLM Policy Optimization [41.15414881730464]
  Vision-Language Models (VLMs) offer a general perceive-reason-act framework for this goal.<n>Previous approaches rely on inefficient and often inaccurate implicit learning of state-values from noisy foresight predictions.<n>We propose a novel test-time computation framework that decouples state evaluation from action generation.
  arXiv  Detail & Related papers  (2026-02-22T22:53:16Z)
• WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning [67.45237332694025]
  Group Relative Policy Optimization is effective for training language models on complex reasoning.<n>We propose Weakly Supervised GRPO, which improves rollout efficiency by converting terminal rewards into correctness-aware guidance.
  arXiv  Detail & Related papers  (2026-02-19T02:43:35Z)
• Stopping Rules for Stochastic Gradient Descent via Anytime-Valid Confidence Sequences [51.56484100374058]
  We study stopping rules for gradient descent (SGD) for convex optimization.<n>We develop an anytime-valid, data-dependent upper confidence sequence for the weighted average suboptimality of projected SGD.<n>These are the first rigorous, time-uniform performance guarantees and finitetime $varepsilon$-optimality certificates.
  arXiv  Detail & Related papers  (2025-12-15T09:26:45Z)
• Decoupled Q-Chunking [63.864222078287575]
  We use chunked critics to estimate the value of short action sequences ("chunks") rather than individual actions, speeding up value backup.<n>Our key insight is to decouple the chunk length of the critic from that of the policy, allowing the policy to operate over shorter action chunks.<n>This design retains the benefits of multi-step value propagation while sidestepping both the open-loop sub-optimality and the difficulty of learning action chunking policies for long action chunks.
  arXiv  Detail & Related papers  (2025-12-11T18:52:51Z)
• SynCast: Synergizing Contradictions in Precipitation Nowcasting via Diffusion Sequential Preference Optimization [62.958457694151384]
  We introduce preference optimization into precipitation nowcasting for the first time, motivated by the success of reinforcement learning from human feedback in large language models.<n>In the first stage, the framework focuses on reducing FAR, training the model to effectively suppress false alarms.
  arXiv  Detail & Related papers  (2025-10-22T16:11:22Z)
• Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling [51.38330727868982]
  We show how action chunking impacts the divergence between a learner and a demonstrator.<n>We propose Bidirectional Decoding (BID), a test-time inference algorithm that bridges action chunking with closed-loop adaptation.<n>Our method boosts the performance of two state-of-the-art generative policies across seven simulation benchmarks and two real-world tasks.
  arXiv  Detail & Related papers  (2024-08-30T15:39:34Z)
• Towards Reliable Uncertainty Quantification via Deep Ensembles in Multi-output Regression Task [0.0]
  This study aims to investigate the deep ensemble approach, an approximate Bayesian inference, in the multi-output regression task. A trend towards underestimation of uncertainty as it increases is observed for the first time. We propose the deep ensemble framework that applies the post-hoc calibration method to improve its uncertainty quantification performance.
  arXiv  Detail & Related papers  (2023-03-28T05:10:57Z)
• Sample-Efficient Optimisation with Probabilistic Transformer Surrogates [66.98962321504085]
  This paper investigates the feasibility of employing state-of-the-art probabilistic transformers in Bayesian optimisation. We observe two drawbacks stemming from their training procedure and loss definition, hindering their direct deployment as proxies in black-box optimisation. We introduce two components: 1) a BO-tailored training prior supporting non-uniformly distributed points, and 2) a novel approximate posterior regulariser trading-off accuracy and input sensitivity to filter favourable stationary points for improved predictive performance.
  arXiv  Detail & Related papers  (2022-05-27T11:13:17Z)

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.