Infant-inspired intrinsically motivated curious robots

Gordon, Goren

doi:10.1016/j.cobeha.2020.05.010

Cited by 9 publications

(4 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Beyond individual differences in interests, we also invent and invest in novel goaldirected behaviors. Variability is so characteristic of children's play that some researchers have suggested that the randomness and variability associated with play might itself be important to learning [31][32][33]. However, neither random behavior, nor a mere preference for doing new things, is likely to support learning in open-ended contexts where rewards are sparse [34].…”

Section: Play In Older Children and Adults: Making Up Problems For Funmentioning

confidence: 99%

In Praise of Folly: Flexible Goals and Human Cognition

Chu

Schulz

2023

Preprint

View full text Add to dashboard Cite

Humans often pursue idiosyncratic goals that can seem remote from functional ends, including information gain. We suggest that this is valuable because goals (even prima facie foolish ones) impose valuable constraints on hypothesis generation and planning. Ideas and plans can be transmitted and adapted intergenerationally and decoupled from their original aims, leading to a proliferation of diverse ideas. If even some of these novel ideas and plans eventually pay off in learning or useful ends, this may be valuable to society as a whole.

show abstract

Section: Play In Older Children and Adults: Making Up Problems For Funmentioning

confidence: 99%

In Praise of Folly: Flexible Goals and Human Cognition

Chu

Schulz

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…This mechanism can help to explain how biological agents select their goals, as well as why behaviors such as being curious and playful should feel good (Kiverstein et al, 2019 ). IM involves an ongoing cycle of finding optimal goals and interesting tasks that evoke emotions with positive valence and it is, therefore, essential for learning and encouraging interaction with the environment (Gordon, 2020 ; Schillaci et al, 2020b ).…”

Section: Agent-related Contextmentioning

confidence: 99%

Grounding Context in Embodied Cognitive Robotics

Valenzo

Ciria

Schillaci³

et al. 2022

Front. Neurorobot.

View full text Add to dashboard Cite

Biological agents are context-dependent systems that exhibit behavioral flexibility. The internal and external information agents process, their actions, and emotions are all grounded in the context within which they are situated. However, in the field of cognitive robotics, the concept of context is far from being clear with most studies making little to no reference to it. The aim of this paper is to provide an interpretation of the notion of context and its core elements based on different studies in natural agents, and how these core contextual elements have been modeled in cognitive robotics, to introduce a new hypothesis about the interactions between these contextual elements. Here, global context is categorized as agent-related, environmental, and task-related context. The interaction of their core elements, allows agents to first select self-relevant tasks depending on their current needs, or for learning and mastering their environment through exploration. Second, to perform a task and continuously monitor its performance. Third, to abandon a task in case its execution is not going as expected. Here, the monitoring of prediction error, the difference between sensorimotor predictions and incoming sensory information, is at the core of behavioral flexibility during situated action cycles. Additionally, monitoring prediction error dynamics and its comparison with the expected reduction rate should indicate the agent its overall performance on executing the task. Sensitivity to performance evokes emotions that function as the driving element for autonomous behavior which, at the same time, depends on the processing of the interacting core elements. Taking all these into account, an interactionist model of contexts and their core elements is proposed. The model is embodied, affective, and situated, by means of the processing of the agent-related and environmental core contextual elements. Additionally, it is grounded in the processing of the task-related context and the associated situated action cycles during task execution. Finally, the model proposed here aims to guide how artificial agents should process the core contextual elements of the agent-related and environmental context to give rise to the task-related context, allowing agents to autonomously select a task, its planning, execution, and monitoring for behavioral flexibility.

show abstract

“…The idiosyncratic nature of children’s play has led some researchers to emphasize not the efficiency or rationality of play but its seeming arbitrariness, leading to proposals that the randomness and variability associated with play may themselves be important to learning (e.g., Dayan & Sejnowski, 1996 ; Gordon, 2020 ; Ossmy et al, 2018 ). However, neither random behavior, nor a mere preference for doing new things, is likely to support learning in open-ended contexts where rewards are sparse (Oudeyer et al, 2007 ).…”

Section: Introductionmentioning

confidence: 99%

Not Playing by the Rules: Exploratory Play, Rational Action, and Efficient Search

Chu

Schulz

2023

Open Mind

View full text Add to dashboard Cite

Recent studies suggest children’s exploratory play is consistent with formal accounts of rational learning. Here we focus on the tension between this view and a nearly ubiquitous feature of human play: In play, people subvert normal utility functions, incurring seemingly unnecessary costs to achieve arbitrary rewards. We show that four-and-five-year-old children not only infer playful behavior from observed violations of rational action (Experiment 1), but themselves take on unnecessary costs during both retrieval (Experiment 2) and search (Experiments 3A–B) tasks, despite acting efficiently in non-playful, instrumental contexts. We discuss the value of such apparently utility-violating behavior and why it might serve learning in the long run.

show abstract

Infant-inspired intrinsically motivated curious robots

Cited by 9 publications

References 46 publications

In Praise of Folly: Flexible Goals and Human Cognition

In Praise of Folly: Flexible Goals and Human Cognition

Grounding Context in Embodied Cognitive Robotics

Not Playing by the Rules: Exploratory Play, Rational Action, and Efficient Search

Contact Info

Product

Resources

About