DeepAI AI Chat
Log In Sign Up

Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain

by   Janarthanan Rajendran, et al.
University of Michigan
Indian Institute Of Technology, Madras
McGill University

Transferring knowledge from prior source tasks in solving a new target task can be useful in several learning applications. The application of transfer poses two serious challenges which have not been adequately addressed. First, the agent should be able to avoid negative transfer, which happens when the transfer hampers or slows down the learning instead of helping it. Second, the agent should be able to selectively transfer, which is the ability to select and transfer from different and multiple source tasks for different parts of the state space of the target task. We propose A2T (Attend, Adapt and Transfer), an attentive deep architecture which adapts and transfers from these source tasks. Our model is generic enough to effect transfer of either policies or value functions. Empirical evaluations on different learning algorithms show that A2T is an effective architecture for transfer by being able to avoid negative transfer while transferring selectively from multiple source tasks in the same domain.


page 9

page 11

page 16

page 17


Characterizing and Avoiding Negative Transfer

When labeled data is scarce for a specific target task, transfer learnin...

Cross-Domain Transfer in Reinforcement Learning using Target Apprentice

In this paper, we present a new approach to Transfer Learning (TL) in Re...

Relatedness Measures to Aid the Transfer of Building Blocks among Multiple Tasks

Multitask Learning is a learning paradigm that deals with multiple diffe...

Towards Robust and Efficient Continual Language Learning

As the application space of language models continues to evolve, a natur...

Learning Stable Classifiers by Transferring Unstable Features

We study transfer learning in the presence of spurious correlations. We ...

Multitasking Evolutionary Algorithm Based on Adaptive Seed Transfer for Combinatorial Problem

Evolutionary computing (EC) is widely used in dealing with combinatorial...

Scalable Transfer Evolutionary Optimization: Coping with Big Task Instances

In today's digital world, we are confronted with an explosion of data an...