Accessibility navigation


Pareto multi-task deep learning

Salvatore D., R., Deyan, D., Giorgio, J., Di Fatta, G. and Nicosia, G. (2020) Pareto multi-task deep learning. In: The 29th International Conference on Artificial Neural Networks (ICANN 2020), 15-18 September 2020. (In Press)

[img] Text - Accepted Version
· Restricted to Repository staff only
· The Copyright of this document has not been checked yet. This may affect its availability.

530kB

It is advisable to refer to the publisher's version if you intend to cite from this work. See Guidance on citing.

Abstract/Summary

Neuroevolution has been used to train Deep Neural Networks on reinforcement learning problems. A few attempts have been made to extend it to address either multi-task or multi-objective optimization problems. This research work presents the Multi-Task Multi-Objective Deep Neuroevolution method, a highly parallelizable algorithm that can be adopted for tackling both multi-task and multi-objective problems. In this method prior knowledge on the tasks is used to explicitly define multiple utility functions, which are optimized simultaneously. Experimental results on some Atari 2600 games, a challenging testbed for deep reinforcement learning algorithms, show that a single neural network with a single set of parameters can outperform previous state of the art techniques. In addition to the standard analysis, all results are also evaluated using the Hypervolume indicator and the Kullback-Leibler divergence to get better insights on the underlying training dynamics. The experimental results show that a neural network trained with the proposed evolution strategy can outperform networks individually trained respectively on each of the tasks.

Item Type:Conference or Workshop Item (Paper)
Refereed:Yes
Divisions:Faculty of Science > School of Mathematical, Physical and Computational Sciences > Department of Computer Science
ID Code:92333

University Staff: Request a correction | Centaur Editors: Update this record

Page navigation