The process of online reinforcement learning also creates a stream of experiences that an agent can store to re-learn from them. In this work, we introduce a concept of artificial perception affecting the dynamics of experience memory replay, which induces a secondary goal-directed drive that complements the main goal defined by the reinforcement function. The different perception dynamics are capable of inducing different "personality" types able to govern the agent behavior, possibly enabling it to exhibit an improved performance over an environment with specific characteristics. Experimental results show that different personalities show different performance levels when facing environment variations, therefore, showcasing the influence of artificial perception in agent's adaptation.

Adaptation of learning agents through artificial perception

Ramicic M.;Bonarini A.
2019

Abstract

The process of online reinforcement learning also creates a stream of experiences that an agent can store to re-learn from them. In this work, we introduce a concept of artificial perception affecting the dynamics of experience memory replay, which induces a secondary goal-directed drive that complements the main goal defined by the reinforcement function. The different perception dynamics are capable of inducing different "personality" types able to govern the agent behavior, possibly enabling it to exhibit an improved performance over an environment with specific characteristics. Experimental results show that different personalities show different performance levels when facing environment variations, therefore, showcasing the influence of artificial perception in agent's adaptation.
ADAPTIVE BEHAVIOR
affective computing; artificial agents; cognitive architectures; perception; Reinforcement learning
computazione affettiva; agenti artificiali; architeture cognitive; percezione; apprendimento per rinforzo;
File in questo prodotto:
File Dimensione Formato  
AdaptationOfLearningAgentsThroughArtificialPerceptionPerception.pdf

accesso aperto

Descrizione: Author's accepted manuscript
: Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione 1.79 MB
Formato Adobe PDF
1.79 MB 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: http://hdl.handle.net/11311/1119596
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact