Loading...
Please wait, while we are loading the content...
Similar Documents
Computational Theories of Curiosity-Driven Learning
| Content Provider | PsyArXiv |
|---|---|
| Author | Oudeyer, Pierre-Yves |
| Description | What are the functions of curiosity? What are the mechanisms of curiosity-driven learning? We approach these questions about the living using concepts and tools from machine learning and developmental robotics. We argue that curiosity-driven learning enables organisms to make discoveries to solve complex problems with rare or deceptive rewards. By fostering exploration and discovery of a diversity of behavioural skills, and ignoring these rewards, curiosity can be efficient to bootstrap learning when there is no information, or deceptive information, about local improvement towards these problems. We also explain the key role of curiosity for efficient learning of world models. We review both normative and heuristic computational frameworks used to understand the mechanisms of curiosity in humans, conceptualizing the child as a sense-making organism. These frameworks enable us to discuss the bi-directional causal links between curiosity and learning, and to provide new hypotheses about the fundamental role of curiosity in self-organizing developmental structures through curriculum learning. We present various developmental robotics experiments that study these mechanisms in action, both supporting these hypotheses to understand better curiosity in humans and opening new research avenues in machine learning and artificial intelligence. Finally, we discuss challenges for the design of experimental paradigms for studying curiosity in psychology and cognitive neuroscience. |
| DOI | 10.31234/osf.io/3p8f6 |
| Language | English |
| Publisher Date | 2018-07-02 |
| Access Restriction | Open |
| Rights License | Copyright 2018 Pierre-Yves Oudeyer |
| Subject Keyword | Social and Behavioral Sciences;Developmental Psychology;Perception Artificial Intelligence Curiosity Curriculum Learning Development Developmental Robotics Free-energy Intrinsic Motivation Learning Progress Hypothesis Lifelong Learning Machine Learning Predictions Reinforcement Learning Rewards Self-organization World Models |
| Content Type | Text |
| Resource Type | Preprint |
| Subject | Social Sciences Developmental and Educational Psychology Psychology |
