A learning process with the plasticity property often requires reinforcement signals to guide the process. However, in some tasks (e.g. maze-navigation), it is very difficult to measure the performance of an agent to provide reinforcements, since the position of the goal is not known. This requires finding the correct behavior among a vast number of possible behaviors without having any feedback. In these cases, an exhaustive search may be needed. However, this might not be feasible especially when optimizing artificial neural networks in continuous domains. In this work, we introduce novelty producing synaptic plasticity (NPSP), where we evolve synaptic plasticity rules to produce as many novel behaviors as possible to find the behavior that can solve the problem. We evaluate the NPSP on deceptive maze environments that require the achievement of subgoals. Our results show that the proposed NPSP produces more novel behaviors compared to Random Search and Random Walk.

Novelty producing synaptic plasticity / Yaman, Anil; Iacca, Giovanni; Mocanu, Decebal Constantin; Fletcher, George; Pechenizkiy, Mykola. - (2020), pp. 93-94. (Intervento presentato al convegno GECCO 2020 tenutosi a Cancun, Mexico nel 8th-12th July 2020) [10.1145/3377929.3389976].

Novelty producing synaptic plasticity

Iacca, Giovanni;
2020-01-01

Abstract

A learning process with the plasticity property often requires reinforcement signals to guide the process. However, in some tasks (e.g. maze-navigation), it is very difficult to measure the performance of an agent to provide reinforcements, since the position of the goal is not known. This requires finding the correct behavior among a vast number of possible behaviors without having any feedback. In these cases, an exhaustive search may be needed. However, this might not be feasible especially when optimizing artificial neural networks in continuous domains. In this work, we introduce novelty producing synaptic plasticity (NPSP), where we evolve synaptic plasticity rules to produce as many novel behaviors as possible to find the behavior that can solve the problem. We evaluate the NPSP on deceptive maze environments that require the achievement of subgoals. Our results show that the proposed NPSP produces more novel behaviors compared to Random Search and Random Walk.
2020
GECCO’20 Companion: Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion
New York, NY
ACM
9781450371278
Yaman, Anil; Iacca, Giovanni; Mocanu, Decebal Constantin; Fletcher, George; Pechenizkiy, Mykola
Novelty producing synaptic plasticity / Yaman, Anil; Iacca, Giovanni; Mocanu, Decebal Constantin; Fletcher, George; Pechenizkiy, Mykola. - (2020), pp. 93-94. (Intervento presentato al convegno GECCO 2020 tenutosi a Cancun, Mexico nel 8th-12th July 2020) [10.1145/3377929.3389976].
File in questo prodotto:
File Dimensione Formato  
3377929.3389976.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 574.49 kB
Formato Adobe PDF
574.49 kB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/273741
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact