Cross-Domain Policy Transfer by Representation Alignment via Multi-Domain Behavioral Cloning

• URL: http://arxiv.org/abs/2407.16912v1
• Date: Wed, 24 Jul 2024 00:13:00 GMT
• Title: Cross-Domain Policy Transfer by Representation Alignment via Multi-Domain Behavioral Cloning
• Authors: Hayato Watahiki, Ryo Iwase, Ryosuke Unno, Yoshimasa Tsuruoka,
• Abstract summary: We present a simple approach for cross-domain policy transfer that learns a shared latent representation across domains and a common abstract policy on top of it. Our approach leverages multi-domain behavioral cloning on unaligned trajectories of proxy tasks and employs maximum mean discrepancy (MMD) as a regularization term to encourage cross-domain alignment.
• Score: 13.674493608667627
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transferring learned skills across diverse situations remains a fundamental challenge for autonomous agents, particularly when agents are not allowed to interact with an exact target setup. While prior approaches have predominantly focused on learning domain translation, they often struggle with handling significant domain gaps or out-of-distribution tasks. In this paper, we present a simple approach for cross-domain policy transfer that learns a shared latent representation across domains and a common abstract policy on top of it. Our approach leverages multi-domain behavioral cloning on unaligned trajectories of proxy tasks and employs maximum mean discrepancy (MMD) as a regularization term to encourage cross-domain alignment. The MMD regularization better preserves structures of latent state distributions than commonly used domain-discriminative distribution matching, leading to higher transfer performance. Moreover, our approach involves training only one multi-domain policy, which makes extension easier than existing methods. Empirical evaluations demonstrate the efficacy of our method across various domain shifts, especially in scenarios where exact domain translation is challenging, such as cross-morphology or cross-viewpoint settings. Our ablation studies further reveal that multi-domain behavioral cloning implicitly contributes to representation alignment alongside domain-adversarial regularization.

Related papers

• xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing [21.37585797507323]
  Cross-domain policy transfer methods mostly aim at learning domain correspondences or corrections to facilitate policy learning. We propose the Cross-Domain Trajectory EDiting framework that employs a specially designed diffusion model for cross-domain trajectory adaptation. Our proposed model architecture effectively captures the intricate dependencies among states, actions, and rewards, as well as the dynamics patterns within target data.
  arXiv  Detail & Related papers  (2024-09-13T10:07:28Z)
• Learning with Alignments: Tackling the Inter- and Intra-domain Shifts for Cross-multidomain Facial Expression Recognition [16.864390181629044]
  We propose a novel Learning with Alignments CMFER framework, named LA-CMFER, to handle both inter- and intra-domain shifts. Based on this, LA-CMFER presents a dual-level inter-domain alignment method to force the model to prioritize hard-to-align samples in knowledge transfer. To address the intra-domain shifts, LA-CMFER introduces a multi-view intra-domain alignment method with a multi-view consistency constraint.
  arXiv  Detail & Related papers  (2024-07-08T07:43:06Z)
• Multi-modal Domain Adaptation for REG via Relation Transfer [46.03480352815051]
  We propose a novel approach to effectively transfer multi-modal knowledge through a specially relation-tailored approach for the Referring Expression Grounding (REG) problem. Our approach tackles the multi-modal domain adaptation problem by simultaneously enriching inter-domain relations and transferring relations between domains.
  arXiv  Detail & Related papers  (2023-09-23T04:02:06Z)
• Domain Generalization via Selective Consistency Regularization for Time Series Classification [16.338176636365752]
  Domain generalization methods aim to learn models robust to domain shift with data from a limited number of source domains. We propose a novel representation learning methodology that selectively enforces prediction consistency between source domains.
  arXiv  Detail & Related papers  (2022-06-16T01:57:35Z)
• Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains [108.11746235308046]
  We propose a novel approach that learns domain-agnostic structured latent embeddings by projecting images from different domains. Our experiments on the challenging DomainNet and DomainNet-LS benchmarks show the superiority of our approach over existing methods.
  arXiv  Detail & Related papers  (2021-07-12T17:57:46Z)
• Domain Consistency Regularization for Unsupervised Multi-source Domain Adaptive Classification [57.92800886719651]
  Deep learning-based multi-source unsupervised domain adaptation (MUDA) has been actively studied in recent years. domain shift in MUDA exists not only between the source and target domains but also among multiple source domains. We propose an end-to-end trainable network that exploits domain Consistency Regularization for unsupervised Multi-source domain Adaptive classification.
  arXiv  Detail & Related papers  (2021-06-16T07:29:27Z)
• AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection [90.18752912204778]
  Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. We propose a novel augmented feature alignment network (AFAN) which integrates intermediate domain image generation and domain-adversarial training. Our approach significantly outperforms the state-of-the-art methods on standard benchmarks for both similar and dissimilar domain adaptations.
  arXiv  Detail & Related papers  (2021-06-10T05:01:20Z)
• Cross-domain Imitation from Observations [50.669343548588294]
  Imitation learning seeks to circumvent the difficulty in designing proper reward functions for training agents by utilizing expert behavior. In this paper, we study the problem of how to imitate tasks when there exist discrepancies between the expert and agent MDP. We present a novel framework to learn correspondences across such domains.
  arXiv  Detail & Related papers  (2021-05-20T21:08:25Z)
• Domain Conditioned Adaptation Network [90.63261870610211]
  We propose a Domain Conditioned Adaptation Network (DCAN) to excite distinct convolutional channels with a domain conditioned channel attention mechanism. This is the first work to explore the domain-wise convolutional channel activation for deep DA networks.
  arXiv  Detail & Related papers  (2020-05-14T04:23:24Z)
• Improve Unsupervised Domain Adaptation with Mixup Training [18.329571222689562]
  We study the problem of utilizing a relevant source domain with abundant labels to build predictive modeling for an unannotated target domain. Recent work observe that the popular adversarial approach of learning domain-invariant features is insufficient to achieve desirable target domain performance. We propose to enforce training constraints across domains using mixup formulation to directly address the generalization performance for target data.
  arXiv  Detail & Related papers  (2020-01-03T01:21:27Z)

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.