Hierarchical curiosity loops and active sensing
نویسندگان
چکیده
A curious agent acts so as to optimize its learning about itself and its environment, without external supervision. We present a model of hierarchical curiosity loops for such an autonomous active learning agent, whereby each loop selects the optimal action that maximizes the agent's learning of sensory-motor correlations. The model is based on rewarding the learner's prediction errors in an actor-critic reinforcement learning (RL) paradigm. Hierarchy is achieved by utilizing previously learned motor-sensory mapping, which enables the learning of other mappings, thus increasing the extent and diversity of knowledge and skills. We demonstrate the relevance of this architecture to active sensing using the well-studied vibrissae (whiskers) system, where rodents acquire sensory information by virtue of repeated whisker movements. We show that hierarchical curiosity loops starting from optimally learning the internal models of whisker motion and then extending to object localization result in free-air whisking and object palpation, respectively.
منابع مشابه
Acetone sensing properties of hierarchical WO3 core-shell microspheres in comparison with commercial nanoparticles
In this work, hierarchical WO3 core-shell microspheres were synthesized via a facile template-free precipitation method. Gas sensing properties of the synthesized powder to acetone and some other volatile organic compounds were comparatively investigated with commercial WO3 nanoparticles. The synthesized and commercial powders were characterized by X-ray diffraction, scanning electron microscop...
متن کاملAcetone sensing properties of hierarchical WO3 core-shell microspheres in comparison with commercial nanoparticles
In this work, hierarchical WO3 core-shell microspheres were synthesized via a facile template-free precipitation method. Gas sensing properties of the synthesized powder to acetone and some other volatile organic compounds were comparatively investigated with commercial WO3 nanoparticles. The synthesized and commercial powders were characterized by X-ray diffraction, scanning electron microscop...
متن کاملCuriosity-Driven Development of Tool Use Precursors: a Computational Model
Studies of child development of tool use precursors show successive but overlapping phases of qualitatively different types of behaviours. We hypothesize that two mechanisms in particular play a role in the structuring of these phases: the intrinsic motivation to explore and the representation used to encode sensorimotor experience. Previous models showed how curiosity-driven learning mechanism...
متن کاملHierarchical Optimistic Region Selection driven by Curiosity
This paper aims to take a step forwards making the term “intrinsic motivation” from reinforcement learning theoretically well founded, focusing on curiositydriven learning. To that end, we consider the setting where, a fixed partition P of a continuous space X being given, and a process ν defined on X being unknown, we are asked to sequentially decide which cell of the partition to select as we...
متن کاملActive regulation of receptor ratios controls integration of quorum-sensing signals in Vibrio harveyi
Quorum sensing is a chemical signaling mechanism used by bacteria to communicate and orchestrate group behaviors. Multiple feedback loops exist in the quorum-sensing circuit of the model bacterium Vibrio harveyi. Using fluorescence microscopy of individual cells, we assayed the activity of the quorum-sensing circuit, with a focus on defining the functions of the feedback loops. We quantitativel...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Neural networks : the official journal of the International Neural Network Society
دوره 32 شماره
صفحات -
تاریخ انتشار 2012