ToM-Dyna-Q: on the integration of reinforcement learning and machine Theory of Mind

The capacity to understand others, or to reason about others’ ways of reasoning about others (including us), is fundamental for an agent to survive in a multi-agent uncertain environment. This reasoning ability, commonly known as Theory of Mind, is instrumental for making effective predictions over...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Kröhling, Dan, Martínez, Ernesto
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2018
Materias:
Ciencias Informáticas
intelligent agents
prediction machines
reinforcement learning
theory of mind
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/73032
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-73032
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
intelligent agents
prediction machines
reinforcement learning
theory of mind
spellingShingle Ciencias Informáticas
intelligent agents
prediction machines
reinforcement learning
theory of mind
Kröhling, Dan
Martínez, Ernesto
ToM-Dyna-Q: on the integration of reinforcement learning and machine Theory of Mind
topic_facet Ciencias Informáticas
intelligent agents
prediction machines
reinforcement learning
theory of mind
description The capacity to understand others, or to reason about others’ ways of reasoning about others (including us), is fundamental for an agent to survive in a multi-agent uncertain environment. This reasoning ability, commonly known as Theory of Mind, is instrumental for making effective predictions over others’ future actions and learning from both real and simulated experience. In this work, a novel architecture for model-based reinforcement learning in a multi-agent setting is proposed. The proposed architecture, called ToM-Dyna-Q, integrates ToM simulation alongside with the well-known Dyna-Q architecture to account for artificial cognition in a shared environment inhabited by multiple agents interacting with each other. Results obtained for the two-player competitive game of Tic-Tac-Toe demonstrate the importance for a given agent of learning, reasoning and planning based on mental simulation modeling of other agents’ goals, beliefs and intentions.
format Objeto de conferencia
Objeto de conferencia
author Kröhling, Dan
Martínez, Ernesto
author_facet Kröhling, Dan
Martínez, Ernesto
author_sort Kröhling, Dan
title ToM-Dyna-Q: on the integration of reinforcement learning and machine Theory of Mind
title_short ToM-Dyna-Q: on the integration of reinforcement learning and machine Theory of Mind
title_full ToM-Dyna-Q: on the integration of reinforcement learning and machine Theory of Mind
title_fullStr ToM-Dyna-Q: on the integration of reinforcement learning and machine Theory of Mind
title_full_unstemmed ToM-Dyna-Q: on the integration of reinforcement learning and machine Theory of Mind
title_sort tom-dyna-q: on the integration of reinforcement learning and machine theory of mind
publishDate 2018
url http://sedici.unlp.edu.ar/handle/10915/73032
work_keys_str_mv AT krohlingdan tomdynaqontheintegrationofreinforcementlearningandmachinetheoryofmind
AT martinezernesto tomdynaqontheintegrationofreinforcementlearningandmachinetheoryofmind
bdutipo_str Repositorios
_version_ 1764820483447980033

Ejemplares similares