Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry

• URL: http://arxiv.org/abs/2606.01098v1
• Date: Sun, 31 May 2026 08:39:57 GMT
• Title: Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry
• Abstract summary: Implicit Drifting Policy (IDP) is a one-step imitation learning framework for robot control.<n>IDP brings the training-time correction of Drifting into policy learning without explicit vector field estimation.
• Score: 46.0185525503119
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative action policies based on diffusion or flow matching excel in behavior cloning, yet their iterative sampling is prohibitive for high-frequency robot control. While recent one-step formulations alleviate this latency, they inevitably discard the intermediate trajectory evolution that provides crucial action correction. Directly recovering this mechanism by explicitly estimating a training-time drifting field is mathematically ill-posed due to extreme conditional demonstration sparsity. We introduce Implicit Drifting Policy (IDP), a one-step imitation learning framework that brings the training-time correction of Drifting into policy learning without explicit vector field estimation. IDP extracts a conditional expert geometry from the local variation of observation-similar expert actions, and compares it against a global reference geometry to isolate condition-specific constraints. This local geometric structure adaptively weights a scalar potential objective. Combined with an expert-proximal terminal evaluation, IDP directly enforces manifold constraints on the one-step generator during training. Extensive evaluations across 2D, 3D, and real-world manipulation tasks show IDP effectively maintains adherence to valid action manifolds, improving upon explicit drifting methods and achieving competitive performance with strong one-step baselines.

Related papers

• 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)
• MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation [65.068801413044]
  Continual test-time adaptation adapts a source-pretrained model to non-stationary, unlabeled target streams.<n>We introduce MoASE, a mixture-of-experts that disentangles domain-agnostic structure from domain-specific texture.
  arXiv  Detail & Related papers  (2026-05-18T01:52:12Z)
• Real-Time Evaluation of Autonomous Systems under Adversarial Attacks [0.29360071145551064]
  This work presents an offline trajectory-learning and adversarial robustness evaluation framework grounded in real-world intersection driving data.<n>We train and compare three trajectory-learning paradigms: Multi-Layer Perceptron (MLP)-based Behavior Cloning (BC), Transformer-based object-tokenized BC, and inverse reinforcement learning (IRL)<n>Inference-time robustness is assessed by subjecting trained policies to gradient-based adversarial perturbations across multiple intersection scenarios.
  arXiv  Detail & Related papers  (2026-05-05T08:30:18Z)
• Evaluation as Evolution: Transforming Adversarial Diffusion into Closed-Loop Curricula for Autonomous Vehicles [43.930171390617055]
  We introduce Evaluation as Evolution ($E2$), a closed-loop framework that transforms adversarial generation into an adaptive evolutionary curriculum.<n>We utilize topology-driven support selection to identify critical interacting agents, and introduce Topological Anchoring to stabilize the process.<n> Empirically, $E2$ improves collision failure discovery by 9.01% on the nuScenes dataset and up to 21.43% on the nuPlan dataset.
  arXiv  Detail & Related papers  (2026-04-08T01:34:05Z)
• Improving Search Agent with One Line of Code [68.58667107354253]
  Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools.<n>We propose textbfSearch textbfAgent textbfPolicy textbfOptimization (textbfSAPO), which stabilizes training via a conditional token-level KL constraint.
  arXiv  Detail & Related papers  (2026-03-10T04:07:39Z)
• Score-Guided Proximal Projection: A Unified Geometric Framework for Rectified Flow Editing [1.0312968200748118]
  Rectified Flow models achieve state-of-the-art generation quality, yet controlling them for precise tasks remains a challenge.<n>Current approaches bifurcate into inversion-based guidance, which suffers from "geometric locking"<n>We propose Score-Guided Proximal Projection, a unified framework that bridges the gap between deterministic optimization and contraction sampling.
  arXiv  Detail & Related papers  (2026-03-05T23:44:45Z)
• Proximal Action Replacement for Behavior Cloning Actor-Critic in Offline Reinforcement Learning [22.17044827069627]
  We propose a plug-and-play training sample replacer to replace low-value actions with high-value actions generated by a stable actor.<n>Experiments show that PAR consistently improves performance and approaches state-of-the-art when combined with the basic TD3+BC.
  arXiv  Detail & Related papers  (2026-02-07T08:44:27Z)
• RFS: Reinforcement Learning with Residual Flow Steering for Dexterous Manipulation [7.500999283386335]
  Residual Flow Steering (RFS) is a data-efficient reinforcement learning framework for adapting pretrained generative policies.<n>RFS steers a pretrained flow-matching policy by jointly optimizing a residual action and a latent noise distribution.<n>We demonstrate the effectiveness of RFS on dexterous manipulation tasks, showing efficient fine-tuning in both simulation and real-world settings.
  arXiv  Detail & Related papers  (2026-02-02T08:11:57Z)
• 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)
• Drift No More? Context Equilibria in Multi-Turn LLM Interactions [58.69551510148673]
  contexts drift is the gradual divergence of a model's outputs from goal-consistent behavior across turns.<n>Unlike single-turn errors, drift unfolds temporally and is poorly captured by static evaluation metrics.<n>We show that multi-turn drift can be understood as a controllable equilibrium phenomenon rather than as inevitable decay.
  arXiv  Detail & Related papers  (2025-10-09T04:48:49Z)
• Time-series Generation by Contrastive Imitation [87.51882102248395]
  We study a generative framework that seeks to combine the strengths of both: Motivated by a moment-matching objective to mitigate compounding error, we optimize a local (but forward-looking) transition policy. At inference, the learned policy serves as the generator for iterative sampling, and the learned energy serves as a trajectory-level measure for evaluating sample quality.
  arXiv  Detail & Related papers  (2023-11-02T16:45:25Z)

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.