paper-with-me

홈 › Papers

Back to the Manifold: Recovering from Out-of-Distribution States

2022-07-18 · Alfredo Reichlin, Giovanni Luca Marchetti, Hang Yin, Ali Ghadirzadeh, Danica Kragic

Learning from previously collected datasets of expert data offers the promise of acquiring robotic policies without unsafe and costly online explorations. However, a major challenge is a distributional shift between the states in the training dataset and the ones visited by the learned policy at the test time. While prior works mainly studied the distribution shift caused by the policy during the offline training, the problem of recovering from out-of-distribution states at the deployment time is not very well studied yet. We alleviate the distributional shift at the deployment time by introducing a recovery policy that brings the agent back to the training manifold whenever it steps out of the in-distribution states, e.g., due to an external perturbation. The recovery policy relies on an approximation of the training data density and a learned equivariant mapping that maps visual observations into a latent space in which translations correspond to the robot actions. We demonstrate the effectiveness of the proposed method through several manipulation experiments on a real robotic platform. Our results show that the recovery policy enables the agent to complete tasks while the behavioral cloning alone fails because of the distributional shift problem.

📄 PDF Abstract BibTeX arXiv:2207.08673

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Fortified Networks: Improving the Robustness of Deep Networks by Modeling the Manifold of Hidden Representations

2018-04-07 · ICLR 2019 5 · Alex Lamb, Jonathan Binas, Anirudh Goyal, Dmitriy Serdyuk 외

Deep networks have achieved impressive results across a variety of important tasks. However a known weakness is a failure to perform well when evaluated on data which differ from the training distribution, even if these …

Manifold-Constrained Energy-Based Transition Models for Offline Reinforcement Learning

2026-02-02 · Zeyu Fang, Zuyuan Zhang, Mahdi Imani, Tian Lan arxiv

Model-based offline reinforcement learning is brittle under distribution shift: policy improvement drives rollouts into state--action regions weakly supported by the dataset, where compounding model error yields severe v…

Reinforcement Learning

Energy-Based Models for Anomaly Detection: A Manifold Diffusion Recovery Approach

2023-10-28 · NeurIPS 2023 11

We present a new method of training energy-based models (EBMs) for anomaly detection that leverages low-dimensional structures within data. The proposed algorithm, Manifold Projection-Diffusion Recovery (MPDR), first per…

Anomaly Detection

Recovering from Out-of-sample States via Inverse Dynamics in Offline Reinforcement Learning

2023-09-21 · NeurIPS 2023 11

In this paper we deal with the state distributional shift problem commonly encountered in offline reinforcement learning during test, where the agent tends to take unreliable actions at out-of-sample (unseen) states. Our…

Generative Learning for Slow Manifolds and Bifurcation Diagrams

2025-04-29 · Ellis R. Crabtree, Dimitris G. Giovanis, Nikolaos Evangelou, Juan M. Bello-Rivas 외

In dynamical systems characterized by separation of time scales, the approximation of so called ``slow manifolds'', on which the long term dynamics lie, is a useful step for model reduction. Initializing on such slow man…