PACE: Phase-Progress-Aware Credit for Long-Horizon Embodied Manipulation

• URL: http://arxiv.org/abs/2608.15026v1
• Date: Sat, 15 Aug 2026 04:25:16 GMT
• Title: PACE: Phase-Progress-Aware Credit for Long-Horizon Embodied Manipulation
• Abstract summary: Policy improvement requires step-level credit signals to distinguish behaviors that advance the task from those that stall or regress.<n>We present PACE, a credit-assignment framework for post-training on long-horizon manipulation.
• Score: 17.66354304197193
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Post-training of vision-language-action (VLA) models typically relies on expert demonstrations and policy interaction trajectories. However, in long-horizon manipulation, a single episode often spans hundreds of control steps and multiple phases, while success or failure is only revealed at episode termination. Policy improvement therefore requires step-level credit signals to distinguish behaviors that advance the task from those that stall or regress. We present PACE, a credit-assignment framework for post-training on long-horizon manipulation, centered on a phase-progress-aware critic. PACE consists of two key modules: (1) the Global-Local Cooperative Value-Correction Critic (GLC-Critic) aggregates visual and motion-difference features within local temporal windows to infer the phase and intra-phase progress of each step, and applies residual correction to a discretized remaining-cost distribution accordingly, enabling step-level credit assignment; (2) Progressive Policy Distillation (PPD) converts credit into positive and negative conditions via task-wise thresholds and trains a credit-conditioned action generation policy: it first protects the pretrained policy with high-credit positive samples, then incorporates all positive and negative credits to learn the quality boundary, and at inference amplifies high-credit behaviors through the difference between conditional outputs. Extensive simulation experiments and diverse real-world robotic-arm experiments demonstrate that PACE consistently achieves significant improvements over the strongest baseline.

Related papers

• PAVE: Predictive Alignment and Value-Guided Evolution for World-Action Policies [17.87859739145508]
  Direct vision-language-action policies generate continuous robot actions efficiently, but standard behavior cloning leaves two complementary gaps.<n>We introduce method, a direct world-action policy that combines outcome-agnostic predictive learning with outcome-aware policy improvement.
  arXiv  Detail & Related papers  (2026-08-31T07:36:11Z)
• Temporal GRPO: Beyond Trajectory-Level Credit in Vision-Language-Action Reinforcement Learning [27.507258147328]
  Outcome-driven reinforcement learning offers a scalable way to post-train vision-language-action (VLA) policies from sparse task-success feedback.<n>On RoboTwin 2.0, Temporal GRPO improves task success and sample efficiency, with consistent gains across task horizons.
  arXiv  Detail & Related papers  (2026-08-13T09:54:14Z)
• IADD-TR: Intervention-Aware Dynamics Decoupling with Targeted Regularization for Model-Based Reinforcement Learning [57.16513298507272]
  We propose IADD-TR, a unified framework combining Intervention-Aware Dynamics Decoupling (IADD) and Targeted Regularization (TR)<n>IADD factorizes transitions into an action-intervention stage and an action-free natural evolution stage, using a zero-action anchor to resolve the non-uniqueness of this two-stage factorization for robust generalization.<n>For policy learning, we derive TR from the efficient influence function of a replay-state policy-gradient functional.
  arXiv  Detail & Related papers  (2026-08-11T08:20:02Z)
• Gated-BEPO: Confidence-Gated Bellman Credit Assignment for Large Language Model Agents [20.885871857379897]
  Training large language model agents in long-horizon environments requires assigning credit from sparse terminal outcomes to individual actions.<n>We propose Gated-BEPO, which derives step-level credit from empirical rollout graphs.
  arXiv  Detail & Related papers  (2026-08-07T06:38:12Z)
• Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning [85.02566758103008]
  Group-Graph Policy Optimization (G2PO) is a novel group-based Reinforcement Learning algorithm tailored for multi-turn agentic tasks.<n>G2PO substantially outperforms state-of-the-art prompt-based and RL baselines, achieving remarkable success rate improvements of up to 22.2% over GRPO.
  arXiv  Detail & Related papers  (2026-06-22T08:12:47Z)
• PHASER: Phase-Aware and Semantic Experience Replay for Vision-Language-Action Models [34.954808072081676]
  We introduce PHASER, an architecture-agnostic continual learning framework.<n>PhaseR employs a phase-centric capacity allocation to guarantee equal memory support for all sub-skills.<n>We also integrate Auto-PC, a lightweight pipeline combining unsupervised action-signal change-point detection with VLM-based semantic verification.
  arXiv  Detail & Related papers  (2026-06-02T13:04:15Z)
• PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations [66.94988600664574]
  We present textbfPRTS (textbfPrimitive textbfReasoning and textbfTasking textbfSystem), a VLA foundation model that reformulates pretraining through Goal-Conditioned Reinforcement Learning.
  arXiv  Detail & Related papers  (2026-04-30T06:14:02Z)
• Learning to Credit the Right Steps: Objective-aware Process Optimization for Visual Generation [57.61006679699323]
  Reinforcement learning has emerged as an effective framework for post-training visual generative models with human preference signals.<n>In modern visual generation, multiple reward models are often used to capture heterogeneous objectives, such as visual quality, motion consistency, and text alignment.<n>We propose Objective-aware Trajectory Credit Assignment (OTCA), a structured framework for fine-grained GRPO training.
  arXiv  Detail & Related papers  (2026-04-21T08:37:13Z)
• AnchorRefine: Synergy-Manipulation Based on Trajectory Anchor and Residual Refinement for Vision-Language-Action Models [60.04879435087352]
  Vision-language-action (VLA) policies generate actions within a single unified space.<n>We propose AnchorRefine, a hierarchical framework that factorizes VLA action modeling into trajectory anchor and residual refinement.<n> Experiments on LIBERO, CALVIN, and real-robot tasks demonstrate that AnchorRefine consistently improves both regression-based and diffusion-based VLA backbones.
  arXiv  Detail & Related papers  (2026-04-20T04:25:24Z)
• Let's Reward Step-by-Step: Step-Aware Contrastive Alignment for Vision-Language Navigation in Continuous Environments [38.97818584066075]
  Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to learn complex reasoning from long-horizon human interactions.<n>Current training paradigms struggle to balance generalization capability, error recovery and training stability.<n>We introduce Step-Aware Contrastive Alignment (SACA), a framework designed to extract dense supervision from imperfect trajectories.
  arXiv  Detail & Related papers  (2026-03-10T14:45:50Z)
• PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation [27.791908160098625]
  PALM builds policy learning around interaction-centric affordance reasoning and subtask progress cues.<n>Palm consistently outperforms baselines in simulation and real-world experiments.
  arXiv  Detail & Related papers  (2026-01-11T21:00:58Z)
• 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)
• 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)

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.