TY - JOUR
T1 - Secretive interaction
T2 - Players and strategies
AU - Skapinakis, Eduardo
N1 - Funding Information:
info:eu-repo/grantAgreement/FCT/Concurso de avaliação no âmbito do Programa Plurianual de Financiamento de Unidades de I&D (2017%2F2018) - Financiamento Base/UIDB%2F00297%2F2020/PT#
info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F00297%2F2020/PT#
info:eu-repo/grantAgreement/FCT/OE/2022.10596.BD/PT#
Publisher Copyright:
© 2024 The Author(s)
PY - 2024/10
Y1 - 2024/10
N2 - We study the behaviour of n players engaged in a conversation, each attempting to predict the behaviour of the others. We prove that, under a certain notion of interaction, it is possible to learn all other players, but, generally, not without being learned back. We then focus on the interaction of two players and consider, for different methodological restrictions based on the philosophy of science, whether some form of secretive learning can be achieved.
AB - We study the behaviour of n players engaged in a conversation, each attempting to predict the behaviour of the others. We prove that, under a certain notion of interaction, it is possible to learn all other players, but, generally, not without being learned back. We then focus on the interaction of two players and consider, for different methodological restrictions based on the philosophy of science, whether some form of secretive learning can be achieved.
KW - Inductive inference
KW - Interactive learning
KW - Learning strategies
KW - Secrecy
UR - http://www.scopus.com/inward/record.url?scp=85199927386&partnerID=8YFLogxK
U2 - 10.1016/j.ic.2024.105196
DO - 10.1016/j.ic.2024.105196
M3 - Article
AN - SCOPUS:85199927386
SN - 0890-5401
VL - 300
JO - Information and Computation
JF - Information and Computation
M1 - 105196
ER -