GRAIL: A Goal-Discovering Robotic Architecture for Intrinsically-Motivated Learning

Santucci, Vieri Giuliano; Baldassarre, Gianluca; Mirolli, Marco

doi:10.1109/tcds.2016.2538961

Cited by 75 publications

(83 citation statements)

References 81 publications

(106 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, classic AI planning implements goal-directed behaviour based on goals and world models, but the resulting systems are quite rigid. This is a limitation because ecological conditions, as also stressed by the Author, always involve challenges such as novel states, goals, and needed actions, on which the agent lacks knowledge (Santucci, Baldassarre, and Mirolli, 2016). We posit that a main way the brain uses to face this lack of knowledge is through processes of manipulation of internal representations of knowledge (alongside actively seeking such knowledge in the external environment, an important issue we cannot further expand here for lack of space, see (Baldassarre and Mirolli, 2013)).…”

Section: Our Proposal: Looking At Principles Of Intelligence In the Bmentioning

confidence: 99%

Special Issue “On Defining Artificial Intelligence”—Commentaries and Author’s Response

Monett

Lewis²,

Þórisson

et al. 2020

Journal of Artificial General Intelligence

Self Cite

View full text Add to dashboard Cite

Pei Wang's paper titled "On Defining Artificial Intelligence" was published in a special issue of the Journal of Artificial General Intelligence (JAGI) in December of last year (Wang, 2019). Wang has been at the forefront of AGI research for over two decades. His non-axiomatic approach to reasoning has stood as a singular example of what may lie beyond narrow AI, garnering interest from NASA and Cisco, among others. We consider his article one of the strongest attempts, since the beginning of the field, to address the long-standing lack of consensus for how to define the field and topic of artificial intelligence (AI). In the recent AGISI survey on defining intelligence (Monett and Lewis, 2018), Pei Wang's definition, The essence of intelligence is the principle of adapting to the environment while working with insufficient knowledge and resources. Accordingly, an intelligent system should rely on finite processing capacity, work in real time, open to unexpected tasks, and learn from experience. This working definition interprets "intelligence" as a form of "relative rationality" (Wang, 2008), 1. Most striking in these numbers is the glaring absence of female authors. A common reason among female academics for rejecting our invitation to contribute was overcommitment. As a community, we may want to think of new, different ways of engaging the full spectrum of AI practitioners if we value inclusion as an essential constituent of a healthy scientific growth. Self determination and willingness to participate are also essential. This is an open access article licensed under the Creative Commons BY-NC-ND License.

show abstract

Section: Our Proposal: Looking At Principles Of Intelligence In the Bmentioning

confidence: 99%

Special Issue “On Defining Artificial Intelligence”—Commentaries and Author’s Response

Monett

Lewis²,

Þórisson

et al. 2020

Journal of Artificial General Intelligence

Self Cite

View full text Add to dashboard Cite

show abstract

“…All the compared systems are developed building on a previous architecture called GRAIL [9], developed for the autonomous discovery and intrinsically motivated learning of goals. Due to paper length constraints here we describe only the features of GRAIL (and the modifications proposed in the current work) that are useful for the understanding of the presented results, and we invite readers to refer to the cited work for further details.…”

Section: B Compared Systemsmentioning

confidence: 99%

Autonomous Reinforcement Learning of Multiple Interrelated Tasks

Santucci

Baldassarre

Cartoni

2019

2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)

Self Cite

View full text Add to dashboard Cite

Autonomous multiple tasks learning is a fundamental capability to develop versatile artificial agents that can act in complex environments. In real-world scenarios, tasks may be interrelated (or "hierarchical") so that a robot has to first learn to achieve some of them to set the preconditions for learning other ones. Even though different strategies have been used in robotics to tackle the acquisition of interrelated tasks, in particular within the developmental robotics framework, autonomous learning in this kind of scenarios is still an open question. Building on previous research in the framework of intrinsically motivated open-ended learning, in this work we describe how this question can be addressed working on the level of task selection, in particular considering the multiple interrelated tasks scenario as an MDP where the system is trying to maximise its competence over all the tasks.

show abstract

“…A particularly illustrative example of recent successful attempt in this direction is the integration of goal representation learning combined with low-level object reaching skill learning in a multi-layered robot cognitive architecture is the work of Santucci et al (2016). In their task, a robot with two arms learns through motor babbling that some movements (i.e.…”

Section: Discussionmentioning

confidence: 99%

Integration of Action, Joint Action and Learning in Robot Cognitive Architectures

Khamassi¹,

Girard²,

Clodic³

et al. 2016

intel

View full text Add to dashboard Cite

Intégration de l’action, de l’action conjointe et de l’apprentissage dans les architectures cognitives robotiques. À l’opposé des recherches en Intelligence Artificielle, où des algorithmes conçus pour des problèmes spécifiques peuvent être testés dans des conditions de simulation parfaitement contrôlée, la Robotique a toujours eu à faire face à la nécessité d’intégrer la perception, la décision et l’exécution de l’action pour pouvoir fonctionner sur des plateformes physiques en interaction dans et avec le monde réel. Cette particularité a obligé les roboticiennes et roboticiens à se poser très tôt la question de comment coordonner efficacement différents systèmes de mémoires, différents niveaux de prise de décision et différents processus d’apprentissage dans des architectures cognitives. En conséquence, les propositions d’architectures robotiques ont souvent été confrontées et nourries par les questionnements sur les architectures cognitives tels qu’abordés en Philosophie, en Psychologie, en Neurosciences, et plus généralement en Sciences Cognitives. Dans cet article, nous passons en revue les travaux robotiques qui ont abordé le problème de l’intégration de différents niveaux d’action et de leurs mécanismes d’apprentissage associés (de la planification des actions orientées vers un but aux simples réflexes ; de la surveillance de l’action aux comportements réactifs guidés par la vision). Nous montrons qu’un tel type d’intégration est nécessaire et suffisant pour permettre à un agent artificiel de montrer un niveau basique de surveillance de sa propre performance, et en conséquence de montrer de plus grandes capacités de flexibilité comportementale, d’autonomie et de généralisation à différents environnements. Nous illustrons cette problématique à travers des exemples expérimentaux sur la coordination de systèmes multiples d’apprentissage au sein d’un même robot, et sur l’application à l’action conjointe lors de la coopération homme-robot. Nous trouvons en effet que des mécanismes partiellement similaires d’intégration des niveaux d’action peuvent fonctionner à la fois pour l’action individuelle et pour l’action conjointe. Enfin, nous mettons en lumière certains des succès et des échecs de ces approches robotiques en espérant nourrir et contribuer aux débats similaires sur l’action qui se posent dans les autres champs des Sciences Cognitives.

show abstract

GRAIL: A Goal-Discovering Robotic Architecture for Intrinsically-Motivated Learning

Cited by 75 publications

References 81 publications

Special Issue “On Defining Artificial Intelligence”—Commentaries and Author’s Response

Special Issue “On Defining Artificial Intelligence”—Commentaries and Author’s Response

Autonomous Reinforcement Learning of Multiple Interrelated Tasks

Integration of Action, Joint Action and Learning in Robot Cognitive Architectures

Contact Info

Product

Resources

About