A Framework for Few-Shot Policy Transfer through Observation Mapping and Behavior Cloning

• URL: http://arxiv.org/abs/2310.08836v1
• Date: Fri, 13 Oct 2023 03:15:42 GMT
• Title: A Framework for Few-Shot Policy Transfer through Observation Mapping and Behavior Cloning
• Authors: Yash Shukla, Bharat Kesari, Shivam Goel, Robert Wright and Jivko Sinapov
• Abstract summary: This work proposes a framework for Few-Shot Policy Transfer between two domains through Observation Mapping and Behavior Cloning. We use Generative Adversarial Networks (GANs) along with a cycle-consistency loss to map the observations between the source and target domains and later use this learned mapping to clone the successful source task behavior policy to the target domain.
• Score: 6.048526012097133
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite recent progress in Reinforcement Learning for robotics applications, many tasks remain prohibitively difficult to solve because of the expensive interaction cost. Transfer learning helps reduce the training time in the target domain by transferring knowledge learned in a source domain. Sim2Real transfer helps transfer knowledge from a simulated robotic domain to a physical target domain. Knowledge transfer reduces the time required to train a task in the physical world, where the cost of interactions is high. However, most existing approaches assume exact correspondence in the task structure and the physical properties of the two domains. This work proposes a framework for Few-Shot Policy Transfer between two domains through Observation Mapping and Behavior Cloning. We use Generative Adversarial Networks (GANs) along with a cycle-consistency loss to map the observations between the source and target domains and later use this learned mapping to clone the successful source task behavior policy to the target domain. We observe successful behavior policy transfer with limited target task interactions and in cases where the source and target task are semantically dissimilar.

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)
• Cross Domain Policy Transfer with Effect Cycle-Consistency [3.3213136251955815]
  Training a robotic policy from scratch using deep reinforcement learning methods can be prohibitively expensive due to sample inefficiency. We propose a novel approach for learning the mapping functions between state and action spaces across domains using unpaired data. Our approach has been tested on three locomotion tasks and two robotic manipulation tasks.
  arXiv  Detail & Related papers  (2024-03-04T13:20:07Z)
• Transfer RL via the Undo Maps Formalism [29.798971172941627]
  Transferring knowledge across domains is one of the most fundamental problems in machine learning. We propose TvD: transfer via distribution matching, a framework to transfer knowledge across interactive domains. We show this objective leads to a policy update scheme reminiscent of imitation learning, and derive an efficient algorithm to implement it.
  arXiv  Detail & Related papers  (2022-11-26T03:44:28Z)
• Omni-Training for Data-Efficient Deep Learning [80.28715182095975]
  Recent advances reveal that a properly pre-trained model endows an important property: transferability. A tight combination of pre-training and meta-training cannot achieve both kinds of transferability. This motivates the proposed Omni-Training framework towards data-efficient deep learning.
  arXiv  Detail & Related papers  (2021-10-14T16:30:36Z)
• Self-Taught Cross-Domain Few-Shot Learning with Weakly Supervised Object Localization and Task-Decomposition [84.24343796075316]
  We propose a task-expansion-decomposition framework for Cross-Domain Few-Shot Learning. The proposed Self-Taught (ST) approach alleviates the problem of non-target guidance by constructing task-oriented metric spaces. We conduct experiments under the cross-domain setting including 8 target domains: CUB, Cars, Places, Plantae, CropDieases, EuroSAT, ISIC, and ChestX.
  arXiv  Detail & Related papers  (2021-09-03T04:23:07Z)
• Multilevel Knowledge Transfer for Cross-Domain Object Detection [26.105283273950942]
  Domain shift is a well known problem where a model trained on a particular domain (source) does not perform well when exposed to samples from a different domain (target) In this work, we address the domain shift problem for the object detection task. Our approach relies on gradually removing the domain shift between the source and the target domains.
  arXiv  Detail & Related papers  (2021-08-02T15:24:40Z)
• Disentangling Transfer and Interference in Multi-Domain Learning [53.34444188552444]
  We study the conditions where interference and knowledge transfer occur in multi-domain learning. We propose new metrics disentangling interference and transfer and set up experimental protocols. We demonstrate our findings on the CIFAR-100, MiniPlaces, and Tiny-ImageNet datasets.
  arXiv  Detail & Related papers  (2021-07-02T01:30:36Z)
• Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation [71.77083272602525]
  UDA attempts to provide efficient knowledge transfer from a labeled source domain to an unlabeled target domain. We propose a contrastive learning approach that adapts category-wise centroids across domains. We extend our method with self-training, where we use a memory-efficient temporal ensemble to generate consistent and reliable pseudo-labels.
  arXiv  Detail & Related papers  (2021-05-05T11:55:53Z)
• Learning Task-oriented Disentangled Representations for Unsupervised Domain Adaptation [165.61511788237485]
  Unsupervised domain adaptation (UDA) aims to address the domain-shift problem between a labeled source domain and an unlabeled target domain. We propose a dynamic task-oriented disentangling network (DTDN) to learn disentangled representations in an end-to-end fashion for UDA.
  arXiv  Detail & Related papers  (2020-07-27T01:21:18Z)
• Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers [138.68213707587822]
  We propose a simple, practical, and intuitive approach for domain adaptation in reinforcement learning. We show that we can achieve this goal by compensating for the difference in dynamics by modifying the reward function. Our approach is applicable to domains with continuous states and actions and does not require learning an explicit model of the dynamics.
  arXiv  Detail & Related papers  (2020-06-24T17:47:37Z)

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.