Transfer Value Iteration Networks

11/11/2019
by   Junyi Shen, et al.
0

Value iteration networks (VINs) have been demonstrated to be effective in predicting outcomes, assuming there is sufficient training data in the target domain. In this paper, we propose a transfer learning approach to leverage knowledge from the source domain to the target domain via automatically learning similarities of actions between two domains, for training the target VIN with only limited training data. The proposed architecture called Transfer Value Iteration Network (TVIN) is shown to empirically outperform VIN between domains with similar state and action spaces. Furthermore, we show that this performance gap is consistent across different maze environments, maze sizes, dataset sizes and also hyperparameters such as iteration counts and kernel sizes.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/26/2018

Cross-position Activity Recognition with Stratified Transfer Learning

Human activity recognition aims to recognize the activities of daily liv...
research
11/24/2022

Cross-domain Transfer of defect features in technical domains based on partial target data

A common challenge in real world classification scenarios with sequentia...
research
11/14/2021

Improving Compound Activity Classification via Deep Transfer and Representation Learning

Recent advances in molecular machine learning, especially deep neural ne...
research
03/02/2023

Target Domain Data induces Negative Transfer in Mixed Domain Training with Disjoint Classes

In practical scenarios, it is often the case that the available training...
research
04/11/2019

Deep Transfer Learning for Single-Channel Automatic Sleep Staging with Channel Mismatch

Many sleep studies suffer from the problem of insufficient data to fully...
research
02/08/2019

Size Independent Neural Transfer for RDDL Planning

Neural planners for RDDL MDPs produce deep reactive policies in an offli...

Please sign up or login with your details

Forgot password? Click here to reset