Domain Adversarial Reinforcement Learning

• URL: http://arxiv.org/abs/2102.07097v1
• Date: Sun, 14 Feb 2021 07:58:41 GMT
• Title: Domain Adversarial Reinforcement Learning
• Authors: Bonnie Li, Vincent Fran\c{c}ois-Lavet, Thang Doan, Joelle Pineau
• Abstract summary: We consider the problem of generalization in reinforcement learning where visual aspects of the observations might differ. The performance of the agent is then reported on new unknown test domains drawn from the MDP distribution. We empirically show that this approach allows achieving a significant generalization improvement to new unseen domains.
• Score: 37.21155002604856
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider the problem of generalization in reinforcement learning where visual aspects of the observations might differ, e.g. when there are different backgrounds or change in contrast, brightness, etc. We assume that our agent has access to only a few of the MDPs from the MDP distribution during training. The performance of the agent is then reported on new unknown test domains drawn from the distribution (e.g. unseen backgrounds). For this "zero-shot RL" task, we enforce invariance of the learned representations to visual domains via a domain adversarial optimization process. We empirically show that this approach allows achieving a significant generalization improvement to new unseen domains.

Related papers

• Cross-Domain Policy Adaptation by Capturing Representation Mismatch [53.087413751430255]
  It is vital to learn effective policies that can be transferred to different domains with dynamics discrepancies in reinforcement learning (RL) In this paper, we consider dynamics adaptation settings where there exists dynamics mismatch between the source domain and the target domain. We perform representation learning only in the target domain and measure the representation deviations on the transitions from the source domain.
  arXiv  Detail & Related papers  (2024-05-24T09:06:12Z)
• Invariance is Key to Generalization: Examining the Role of Representation in Sim-to-Real Transfer for Visual Navigation [35.01394611106655]
  Key to generalization is representations that are rich enough to capture all task-relevant information. We experimentally study such a representation for visual navigation. We show that our representation reduces the A-distance between the training and test domains.
  arXiv  Detail & Related papers  (2023-10-23T15:15:19Z)
• Gated Domain Units for Multi-source Domain Generalization [14.643490853965385]
  Distribution shift (DS) occurs when a dataset at test time differs from the dataset at training time. We introduce a modular neural network layer consisting of Gated Domain Units (GDUs) that learn a representation for each latent elementary distribution. During inference, a weighted ensemble of learning machines can be created by comparing new observations with the representations of each elementary distribution.
  arXiv  Detail & Related papers  (2022-06-24T18:12:38Z)
• Unsupervised Domain Generalization by Learning a Bridge Across Domains [78.855606355957]
  Unsupervised Domain Generalization (UDG) setup has no training supervision in neither source nor target domains. Our approach is based on self-supervised learning of a Bridge Across Domains (BrAD) - an auxiliary bridge domain accompanied by a set of semantics preserving visual (image-to-image) mappings to BrAD from each of the training domains. We show how using an edge-regularized BrAD our approach achieves significant gains across multiple benchmarks and a range of tasks, including UDG, Few-shot UDA, and unsupervised generalization across multi-domain datasets.
  arXiv  Detail & Related papers  (2021-12-04T10:25:45Z)
• On Learning Domain-Invariant Representations for Transfer Learning with Multiple Sources [21.06231751703114]
  We develop novel upper-bounds for the target general loss which appeal to us to define two kinds of domain-invariant representations. We study the pros and cons as well as the trade-offs of enforcing learning each domain-invariant representation.
  arXiv  Detail & Related papers  (2021-11-27T06:14:28Z)
• Fishr: Invariant Gradient Variances for Out-of-distribution Generalization [98.40583494166314]
  Fishr is a learning scheme to enforce domain invariance in the space of the gradients of the loss function. Fishr exhibits close relations with the Fisher Information and the Hessian of the loss. In particular, Fishr improves the state of the art on the DomainBed benchmark and performs significantly better than Empirical Risk Minimization.
  arXiv  Detail & Related papers  (2021-09-07T08:36:09Z)
• Improving Transferability of Domain Adaptation Networks Through Domain Alignment Layers [1.3766148734487902]
  Multi-source unsupervised domain adaptation (MSDA) aims at learning a predictor for an unlabeled domain by assigning weak knowledge from a bag of source models. We propose to embed Multi-Source version of DomaIn Alignment Layers (MS-DIAL) at different levels of the predictor. Our approach can improve state-of-the-art MSDA methods, yielding relative gains of up to +30.64% on their classification accuracies.
  arXiv  Detail & Related papers  (2021-09-06T18:41:19Z)
• Domain Generalization via Gradient Surgery [5.38147998080533]
  In real-life applications, machine learning models often face scenarios where there is a change in data distribution between training and test domains. In this work, we characterize the conflicting gradients emerging in domain shift scenarios and devise novel gradient agreement strategies.
  arXiv  Detail & Related papers  (2021-08-03T16:49:25Z)
• Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation [109.73983088432364]
  We propose the first method that aims to simultaneously learn invariant representations and risks under the setting of semi-supervised domain adaptation (Semi-DA) We introduce the LIRR algorithm for jointly textbfLearning textbfInvariant textbfRepresentations and textbfRisks.
  arXiv  Detail & Related papers  (2020-10-09T15:42:35Z)
• 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.