DeepAI AI Chat
Log In Sign Up

Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptation

03/12/2021
by   Karol Arndt, et al.
0

Domain adaptation is a common problem in robotics, with applications such as transferring policies from simulation to real world and lifelong learning. Performing such adaptation, however, requires informative data about the environment to be available during the adaptation. In this paper, we present domain curiosity – a method of training exploratory policies that are explicitly optimized to provide data that allows a model to learn about the unknown aspects of the environment. In contrast to most curiosity methods, our approach explicitly rewards learning, which makes it robust to environment noise without sacrificing its ability to learn. We evaluate the proposed method by comparing how much a model can learn about environment dynamics given data collected by the proposed approach, compared to standard curious and random policies. The evaluation is performed using a toy environment, two simulated robot setups, and on a real-world haptic exploration task. The results show that the proposed method allows data-efficient and accurate estimation of dynamics.

READ FULL TEXT

page 1

page 7

10/16/2020

Few-shot model-based adaptation in noisy conditions

Few-shot adaptation is a challenging problem in the context of simulatio...
03/08/2023

Learning Exploration Strategies to Solve Real-World Marble Runs

Tasks involving locally unstable or discontinuous dynamics (such as bifu...
09/28/2022

Focused Adaptation of Dynamics Models for Deformable Object Manipulation

In order to efficiently learn a dynamics model for a task in a new envir...
11/19/2019

MANGA: Method Agnostic Neural-policy Generalization and Adaptation

In this paper we target the problem of transferring policies across mult...
11/09/2020

Localising In Complex Scenes Using Balanced Adversarial Adaptation

Domain adaptation and generative modelling have collectively mitigated t...
10/26/2017

DoShiCo: a Domain Shift Challenge for Control

Training deep neural control networks end-to-end for real-world applicat...
02/18/2022

Echo-aware Adaptation of Sound Event Localization and Detection in Unknown Environments

Our goal is to develop a sound event localization and detection (SELD) s...