Warp RL: Reshaping Base Policy Distributions for Dynamics Adaptation

• URL: http://arxiv.org/abs/2606.31043v2
• Date: Wed, 01 Jul 2026 05:04:39 GMT
• Title: Warp RL: Reshaping Base Policy Distributions for Dynamics Adaptation
• Abstract summary: Residual reinforcement learning adapts a pretrained robot policy by learning an additive correction to its actions.<n>We show that when the base distribution is geometrically mismatched to the shifted system, residual correction can underperform even the unadapted policy.<n>We propose Warp RL, a policy adaptation method that replaces additive residuals with an invertible, state-conditioned transformation of the base policy's action distribution.
• Score: 3.3656696418661975
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Residual reinforcement learning adapts a pretrained robot policy by learning an additive correction to its actions. While effective when adaptation amounts to shifting the base policy's action distribution, additive corrections cannot change the distribution's shape, scale, or state-dependent geometry -- limitations we formalize as wrong variance, miscalibrated confidence, and non-uniform correction. We show that these matter under dynamics shift: when the base distribution is geometrically mismatched to the shifted system, residual correction can underperform even the unadapted policy. We propose Warp RL, a policy adaptation method that replaces additive residuals with an invertible, state-conditioned transformation of the base policy's action distribution. Instantiated with monotonic rational-quadratic spline flows (arXiv:1906.04032), Warp RL preserves identity initialization, strictly generalizes additive residual correction, and exposes a structured adaptation space suitable for both policy-gradient and gradient-free optimization. Across a variety of ManiSkill3 manipulation tasks with controlled dynamics shifts, Warp RL matches residual correction when translation is sufficient and substantially outperforms it when adaptation requires distributional reshaping. We further demonstrate that warping can replace additive correction in an off-policy sim-to-real pipeline, achieving comparable success rate with 30% faster task completion on a real-robot peg-insertion task.

Related papers

• ORPA: Online Residual Policy Adaptation for Robot Manipulation Control with Human Feedback [1.711436622393758]
  Online Residual Policy Adaptation (ORPA) is a framework that enables feedback-driven correction of robot actions without modifying the underlying policy parameters.<n>ORPA augments a pretrained control policy with a lightweight, feedback-conditioned module that predicts residual adjustments directly in joint space.<n>We evaluate ORPA on a set of precision-sensitive manipulation tasks using the ALOHA platform, demonstrating improvements in success rate and recovery from small perturbations compared to baseline control policies and rule-based inverse kinematics corrections.
  arXiv  Detail & Related papers  (2026-08-18T03:30:12Z)
• ReFPO: Reflow Regularization for Flow Matching Policy Gradients [58.32178725687043]
  We present a simple online RL method that adds explicit Reflow regularization to Flow Matching Policy Gradients.<n>We experimentally demonstrate that ReFPO improves average performance and discretization across GridWorld, MuJoCo Playground, and high-dimensional Humanoid Control tasks.
  arXiv  Detail & Related papers  (2026-06-19T04:23:10Z)
• Transfer Learning Across Policy Regimes in Adaptive Multi-Agent Systems [0.0]
  Policy models often assume that the relationship between a policy instrument and its outcome remains stable across institutional conditions.<n>This paper studies such regime change as a transfer-learning problem in adaptive multi-agent systems.
  arXiv  Detail & Related papers  (2026-06-15T10:16:01Z)
• Rethinking the Divergence Regularization in LLM RL [56.952725733148746]
  Reinforcement learning (RL) has become a key component of post-training large language models (LLMs)<n>We propose Divergence Regularized Policy Optimization (DRPO), which replaces the hard mask with a smooth advantage-weighted quadratic regularizer on policy shift.<n>DRPO preserves the same trust-region geometry as DPPO while inducing bounded, continuous gradient weights.
  arXiv  Detail & Related papers  (2026-06-08T17:58:23Z)
• One-Way Policy Optimization for Self-Evolving LLMs [63.8638342097375]
  Reinforcement Learning with Verifiable Rewards (RLVR) has become a promising paradigm for scaling reasoning capabilities of Large Language Models (LLMs)<n>We propose One-Way Policy Optimization (OWPO), a method based on the principle of decoupling optimization direction from update magnitude.<n> Experimental results demonstrate that OWPO outperforms strong baselines, including DAPO, OPD, and MOPD.
  arXiv  Detail & Related papers  (2026-05-21T08:25:27Z)
• Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent [53.828537014796574]
  Online off-policy reinforcement learning (RL) is shaped by two choices: the policy class and the update rule.<n>We propose MeanFlow Policies, a one-step generative policy class that maps noise to actions through a MeanFlow transformation.<n>Across seven MuJoCo benchmarks, S improves over Gaussian and generative baselines while retaining single-step inference efficiency.
  arXiv  Detail & Related papers  (2026-05-20T15:14:14Z)
• 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)
• VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training [18.849117699859622]
  Training stability is a central challenge in reinforcement learning for large language models.<n>We propose Variational sEquence-level Soft Policy Optimization (VESPO)<n> Experiments on mathematical reasoning benchmarks show that VESPO maintains stable training under staleness ratios up to 64x and fully asynchronous execution.
  arXiv  Detail & Related papers  (2026-02-11T09:48:08Z)
• Recurrent Equivariant Constraint Modulation: Learning Per-Layer Symmetry Relaxation from Data [36.287199718605]
  Equivariant neural networks exploit underlying task symmetries to improve generalization.<n>We propose Recurrent Equivariant Constraint Modulation (RECM), a layer-wise constraint modulation mechanism.<n>RECM learns appropriate relaxation levels solely from the training signal and the symmetry properties of each layer's input-target distribution.
  arXiv  Detail & Related papers  (2026-02-02T21:59:35Z)
• 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)
• GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping [63.33669214116784]
  GRPO-Guard is a simple yet effective enhancement to existing GRPO frameworks.<n>It restores a balanced and step-consistent importance ratio, ensuring that PPO clipping properly constrains harmful updates.<n>It substantially mitigates implicit over-optimization without relying on heavy KL regularization.
  arXiv  Detail & Related papers  (2025-10-25T14:51:17Z)

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.