Learning to Multi-Task by Active Sampling

by   Sahil Sharma, et al.

One of the long-standing challenges in Artificial Intelligence for learning goal-directed behavior is to build a single agent which can solve multiple tasks. Recent progress in multi-task learning for goal-directed sequential problems has been in the form of distillation based learning wherein a student network learns from multiple task-specific expert networks by mimicking the task-specific policies of the expert networks. While such approaches offer a promising solution to the multi-task learning problem, they require supervision from large expert networks which require extensive data and computation time for training. In this work, we propose an efficient multi-task learning framework which solves multiple goal-directed tasks in an on-line setup without the need for expert supervision. Our work uses active learning principles to achieve multi-task learning by sampling the harder tasks more than the easier ones. We propose three distinct models under our active sampling framework. An adaptive method with extremely competitive multi-tasking performance. A UCB-based meta-learner which casts the problem of picking the next task to train on as a multi-armed bandit problem. A meta-learning method that casts the next-task picking problem as a full Reinforcement Learning problem and uses actor critic methods for optimizing the multi-tasking performance directly. We demonstrate results in the Atari 2600 domain on seven multi-tasking instances: three 6-task instances, one 8-task instance, two 12-task instances and one 21-task instance.


page 7

page 12

page 13

page 22

page 23

page 25


When is an SHM problem a Multi-Task-Learning problem?

Multi-task neural networks learn tasks simultaneously to improve individ...

Multi-Task Meta Learning: learn how to adapt to unseen tasks

This work aims to integrate two learning paradigms Multi-Task Learning (...

Multi-Task Learning with Sequence-Conditioned Transporter Networks

Enabling robots to solve multiple manipulation tasks has a wide range of...

An Active Learning Framework for Efficient Robust Policy Search

Robust Policy Search is the problem of learning policies that do not deg...

Deep Elastic Networks with Model Selection for Multi-Task Learning

In this work, we consider the problem of instance-wise dynamic network m...

Efficient Reinforcement Learning in Resource Allocation Problems Through Permutation Invariant Multi-task Learning

One of the main challenges in real-world reinforcement learning is to le...

In-BoXBART: Get Instructions into Biomedical Multi-Task Learning

Single-task models have proven pivotal in solving specific tasks; howeve...

Please sign up or login with your details

Forgot password? Click here to reset