Skip to Main content Skip to Navigation
Conference papers

Universal Notice Network: Transferable Knowledge Among Agents

Abstract : Being able to learn and transfer skills from one agent to another is a fundamental feature in constructing even more intelligent behaviors. In this paper, we introduce a new kind of architecture and information pipeline that aims to enable the transmission of skills from one robot to one or several others. The Universal Notice Network (UNN) originality lies in the fact that it clearly distinguishes knowledge necessary to solve the task from the agent intrinsic perceptions and capabilities, hence increasing its reusability and its potential transmission to other agents. In various experiments, focusing on manipulation and comanipulation tasks in original environments, we demonstrate the capabilities of the proposed method that takes advantage of reinforcement learning algorithms and domain knowledge, such as forward geometric model and inverse kinematics. In particular, we show that a learned UNN through the interactions of an agent with its environment is transmissible to other agents, conserving a similar perfomance level.
Complete list of metadata
Contributor : Benoit Thuilot Connect in order to contact the contributor
Submitted on : Sunday, December 6, 2020 - 7:12:59 PM
Last modification on : Tuesday, November 16, 2021 - 4:30:38 AM
Long-term archiving on: : Sunday, March 7, 2021 - 6:24:00 PM


Files produced by the author(s)


Distributed under a Creative Commons Attribution 4.0 International License



Mehdi Mounsif, Sebastien Lengagne, Benoit Thuilot, Lounis Adouane. Universal Notice Network: Transferable Knowledge Among Agents. 6th International Conference on Control, Decision and Information Technologies (CoDIT 2019), Apr 2019, Paris, France. pp.563-568, ⟨10.1109/CoDIT.2019.8820403⟩. ⟨hal-03042500⟩



Record views


Files downloads