Opinion: Towards Unified Expressive Policy Optimization for Robust Robot Learning

• URL: http://arxiv.org/abs/2511.10087v1
• Date: Fri, 14 Nov 2025 01:31:10 GMT
• Title: Opinion: Towards Unified Expressive Policy Optimization for Robust Robot Learning
• Abstract summary: We propose UEPO, a unified generative framework inspired by large language model pretraining and fine-tuning strategies.<n>Our contributions are threefold: (1) a multi-seed dynamics-aware diffusion policy that efficiently captures diverse modalities without training multiple models; (2) a dynamic divergence regularization mechanism that enforces physically meaningful policy diversity; and (3) a diffusion-based data augmentation module that enhances dynamics model generalization.
• Score: 8.277689331569787
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Offline-to-online reinforcement learning (O2O-RL) has emerged as a promising paradigm for safe and efficient robotic policy deployment but suffers from two fundamental challenges: limited coverage of multimodal behaviors and distributional shifts during online adaptation. We propose UEPO, a unified generative framework inspired by large language model pretraining and fine-tuning strategies. Our contributions are threefold: (1) a multi-seed dynamics-aware diffusion policy that efficiently captures diverse modalities without training multiple models; (2) a dynamic divergence regularization mechanism that enforces physically meaningful policy diversity; and (3) a diffusion-based data augmentation module that enhances dynamics model generalization. On the D4RL benchmark, UEPO achieves +5.9\% absolute improvement over Uni-O4 on locomotion tasks and +12.4\% on dexterous manipulation, demonstrating strong generalization and scalability.

Related papers

• Drift-Based Policy Optimization: Native One-Step Policy Learning for Online Robot Control [42.5826210330077]
  Multi-step generative policies achieve strong performance in robotic manipulation by modeling multimodal action distributions.<n>Each action requires tens to hundreds of network function evaluations.<n>We propose a two-stage framework for native one-step generative policies that shifts refinement from inference to training.
  arXiv  Detail & Related papers  (2026-04-04T01:32:01Z)
• PCHC: Enabling Preference Conditioned Humanoid Control via Multi-Objective Reinforcement Learning [50.63196995993855]
  We propose a novel framework leveraging Multi-Objective Reinforcement Learning (MORL) to achieve Preference-Conditioned Humanoid Control (PCHC)<n>Our framework enables a single, preference-conditioned policy to exhibit a wide spectrum of diverse behaviors.
  arXiv  Detail & Related papers  (2026-03-25T07:55:37Z)
• A Review of Online Diffusion Policy RL Algorithms for Scalable Robotic Control [21.22244612145334]
  Diffusion policies have emerged as a powerful approach for robotic control.<n>Online Diffusion Policy Reinforcement Learning (Online DPRL) algorithms for scalable robotic control systems are studied.
  arXiv  Detail & Related papers  (2026-01-05T05:19:23Z)
• Bridging VLMs and Embodied Intelligence with Deliberate Practice Policy Optimization [72.20212909644017]
  Deliberate Practice Policy Optimization (DPPO) is a metacognitive Metaloop'' training framework.<n>DPPO alternates between supervised fine-tuning (competence expansion) and reinforcement learning (skill refinement)<n> Empirically, training a vision-language embodied model with DPPO, referred to as Pelican-VL 1.0, yields a 20.3% performance improvement over the base model.<n>We are open-sourcing both the models and code, providing the first systematic framework that alleviates the data and resource bottleneck.
  arXiv  Detail & Related papers  (2025-11-20T17:58:04Z)
• Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models [31.470613363668672]
  Adaptive Divergence Regularized Policy Optimization automatically adjusts regularization strength based on advantage estimates.<n>Our implementation with Wasserstein-2 regularization for flow matching generative models achieves remarkable results on text-to-image generation.<n> ADRPO generalizes to KL-regularized fine-tuning of both text-only LLMs and multi-modal reasoning models.
  arXiv  Detail & Related papers  (2025-10-20T19:46:02Z)
• Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces [57.466101098183884]
  Reinforcement learning (RL) struggles to scale to large, action spaces common in many real-world problems.<n>This paper introduces a novel framework for training discrete diffusion models as highly effective policies in complex settings.
  arXiv  Detail & Related papers  (2025-09-26T21:53:36Z)
• Policy-Driven World Model Adaptation for Robust Offline Model-based Reinforcement Learning [6.189693079685375]
  offline model-based RL (MBRL) explicitly learns a world model from a static dataset.<n>We propose a framework that dynamically adapts the world model alongside the policy.<n>We benchmark our algorithm on twelve noisy D4RL MuJoCo tasks and three Tokamak Control tasks, demonstrating its state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-05-19T20:14:33Z)
• LAMeTA: Intent-Aware Agentic Network Optimization via a Large AI Model-Empowered Two-Stage Approach [68.198383438396]
  We present LAMeTA, a Large AI Model (LAM)-empowered Two-stage Approach for intent-aware agentic network optimization.<n>First, we propose Intent-oriented Knowledge Distillation (IoKD), which efficiently distills intent-understanding capabilities.<n>Second, we develop Symbiotic Reinforcement Learning (SRL), integrating E-LAMs with a policy-based DRL framework.
  arXiv  Detail & Related papers  (2025-05-18T05:59:16Z)
• Imagine-2-Drive: Leveraging High-Fidelity World Models via Multi-Modal Diffusion Policies [9.639797094021988]
  World Model-based Reinforcement Learning (WMRL) enables sample efficient policy learning.<n>We propose Imagine-2-Drive, a novel WMRL framework that integrates a high-fidelity world model with a multi-modal diffusion-based policy actor.<n>By training DPA within DiffDreamer, our method enables robust policy learning with minimal online interactions.
  arXiv  Detail & Related papers  (2024-11-15T13:17:54Z)
• When Parameter-efficient Tuning Meets General-purpose Vision-language Models [65.19127815275307]
  PETAL revolutionizes the training process by requiring only 0.5% of the total parameters, achieved through a unique mode approximation technique. Our experiments reveal that PETAL not only outperforms current state-of-the-art methods in most scenarios but also surpasses full fine-tuning models in effectiveness.
  arXiv  Detail & Related papers  (2023-12-16T17:13:08Z)
• Beyond Conservatism: Diffusion Policies in Offline Multi-agent Reinforcement Learning [29.31031504054288]
  We present a novel Diffusion Offline Multi-agent Model (DOM2) for offline Multi-Agent Reinforcement Learning (MARL) DOM2 enhances policy expressiveness and diversity based on diffusion. It can achieve state-of-the-art performance with $20+$ times less data compared to existing algorithms.
  arXiv  Detail & Related papers  (2023-07-04T04:40:54Z)
• Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning [70.20191211010847]
  Offline reinforcement learning (RL) aims to learn an optimal policy using a previously collected static dataset. We introduce Diffusion Q-learning (Diffusion-QL) that utilizes a conditional diffusion model to represent the policy. We show that our method can achieve state-of-the-art performance on the majority of the D4RL benchmark tasks.
  arXiv  Detail & Related papers  (2022-08-12T09:54:11Z)
• Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning [124.9856253431878]
  We decompose the task of learning a global dynamics model into two stages: (a) learning a context latent vector that captures the local dynamics, then (b) predicting the next state conditioned on it. In order to encode dynamics-specific information into the context latent vector, we introduce a novel loss function that encourages the context latent vector to be useful for predicting both forward and backward dynamics. The proposed method achieves superior generalization ability across various simulated robotics and control tasks, compared to existing RL schemes.
  arXiv  Detail & Related papers  (2020-05-14T08:10:54Z)

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.