Learning Generalizable Skill Policy with Data-Efficient Unsupervised RL

• URL: http://arxiv.org/abs/2607.00392v1
• Date: Wed, 01 Jul 2026 03:34:29 GMT
• Title: Learning Generalizable Skill Policy with Data-Efficient Unsupervised RL
• Abstract summary: We propose GenDa, a unified framework for robust unsupervised reinforcement learning.<n>First, we introduce a skill relabeling mechanism to mitigate non-stationarity.<n>Second, we propose a Complementary Information Bottleneck (CIB), encouraging the learned skill policy to focus on ego-centric features.
• Score: 7.80766284546658
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Unsupervised Reinforcement Learning (URL) aims to pre-train scalable, skill-conditioned policies without extrinsic rewards, serving as a foundation for downstream control tasks. Despite recent progress, we argue that current off-policy URL methods are limited by two critical, overlooked bottlenecks: (1) non-stationary skill semantics and (2) brittle generalization. To address these challenges, we propose GenDa (Generalizable Data-efficient Agent), a unified framework for robust unsupervised reinforcement learning. First, we introduce a skill relabeling mechanism to mitigate non-stationarity and significantly improve data efficiency for pre-training. Second, we propose a Complementary Information Bottleneck (CIB), encouraging the learned skill policy to focus on ego-centric features and become robust to distribution shifts for downstream tasks. Through various experiments, we demonstrate that GenDa significantly enhances the scalability of URL with superior generalizability and data efficiency. Our code and videos are available at https://ihatebroccoli.github.io/official-GenDa.

Related papers

• OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning [38.54413500261524]
  On-policy self-distillation offers dense token-level supervision.<n>textbfOPID (textbfOn-textbfPolicy Sktextbfill textbfDistillation) is a framework that extracts skill supervision directly from completed on trajectories.
  arXiv  Detail & Related papers  (2026-06-25T09:24:09Z)
• Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning [21.705096559151286]
  We show that offline reinforcement learning can be used to harness non-expert data to enhance the performance of imitation learning policies.<n>Our approach shows that broadening the support of the policy distribution can allow imitation algorithms augmented by offline RL to solve tasks robustly.
  arXiv  Detail & Related papers  (2025-10-22T11:43:39Z)
• Diffusion Guidance Is a Controllable Policy Improvement Operator [98.11511661904618]
  CFGRL is trained with the simplicity of supervised learning, yet can further improve on the policies in the data.<n>On offline RL tasks, we observe a reliable trend -- increased guidance weighting leads to increased performance.
  arXiv  Detail & Related papers  (2025-05-29T14:06:50Z)
• RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning [53.8293458872774]
  We propose Reinforcement Learning Distilled Generalists (RLDG) to generate high-quality training data for finetuning generalist policies.<n>We demonstrate that generalist policies trained with RL-generated data consistently outperform those trained with human demonstrations.<n>Our results suggest that combining task-specific RL with generalist policy distillation offers a promising approach for developing more capable and efficient robotic manipulation systems.
  arXiv  Detail & Related papers  (2024-12-13T04:57:55Z)
• Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration [54.8229698058649]
  Unlabeled offline trajectory data can be leveraged to learn efficient exploration strategies.<n>Our method SUPE consistently outperforms prior strategies across a suite of 42 long-horizon, sparse-reward tasks.
  arXiv  Detail & Related papers  (2024-10-23T17:58:45Z)
• Foundation Policies with Hilbert Representations [54.44869979017766]
  We propose an unsupervised framework to pre-train generalist policies from unlabeled offline data. Our key insight is to learn a structured representation that preserves the temporal structure of the underlying environment. Our experiments show that our unsupervised policies can solve goal-conditioned and general RL tasks in a zero-shot fashion.
  arXiv  Detail & Related papers  (2024-02-23T19:09:10Z)
• Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach [95.74102207187545]
  We show that a prior-free autonomous data augmentation's objective can be derived from a representation learning principle. We then propose a practical surrogate to the objective that can be efficiently optimized and integrated seamlessly into existing methods.
  arXiv  Detail & Related papers  (2022-11-02T02:02:51Z)
• Simplifying Deep Reinforcement Learning via Self-Supervision [51.2400839966489]
  Self-Supervised Reinforcement Learning (SSRL) is a simple algorithm that optimize policies with purely supervised losses. We show that SSRL is surprisingly competitive to contemporary algorithms with more stable performance and less running time.
  arXiv  Detail & Related papers  (2021-06-10T06:29:59Z)

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.