Intrinsically Motivated Learning in Natural and Artificial Systems

By Gianluca Baldassarre, Marco Mirolli. 2013

281 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Reinforcement Learning, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Reinforcement Learning

In Meta & Continual Learning

Citations in the corpus

Novelty or Surprise? (2013, background): “This is one of the ﬁrst proposals for how ideas related to what psychologists call intrinsic motivation can be implemented in a machine learning system, and much additional research has been lately done in this area (Baldassarre and Mirolli, 2013).”
Towards a neuroscience of active sampling and curiosity (2018, unknown): “There has been a growing interest in the field of artificial intelligence, machine learning and robotics for curiosity-driven learning algorithms (also called intrinsically motivated learning) 96,117,126,127 .”
Curiosity-Driven Development of Tool Use Precursors: a Computational Model (2016, background): “Keywords: curiosity-driven learning; tool use; goal babbling; overlapping waves; developmental trajectory; HACOB model”
Reinforcement learning for control: Performance, stability, and deep approximators (2018, background): “Other directed exploration methods include those that add to the original rewards an extra exploration-inducing term, called intrinsic reward, when visiting states that are deemed interesting (Barto, 2013).”
Multi-Armed Bandits for Intelligent Tutoring Systems (2013, background): “Such models were shown to reproduce qualitative properties of spontaneous exploration and information seeking in humans [33, 41, 6].”
The minority report: some common assumptions to reconsider in the modelling of the brain and behaviour (2016, background): “Of all the chapters in Baldassarre and Mirolli (2013), only one mentions map-learning: ‘Scott and Markovitch (1989) presented a curiosity-driven search method by which an agent’s attention was continually directed to the area of highest uncertainty in the current representation, thus steadily…”
Self-organization of early vocal development in infants and machines: the role of intrinsic motivation (2014, background): “…of the internal model of the sensorimotor mapping, and the intrinsic motivation mechanism which allows the learner to decide adaptively which vocalization to experiment at given moments during its development, and whether to do so through self-exploration or through imitation of external sounds.”
Surprise and Curiosity for Big Data Robotics (2014, background): “…been explored in the context of option learning (Singh et al 2005, Simsek and Barto 2006, Schembri et al 2007), developmental robot exploration (Schmidhuber 1991, Oudeyer et al, 2007), and exploration and exploitation in reinforcement learning (see Baldassarre and Mirolli 2013 for an overview).”