Adaptive Prior Selection for Repertoire-based Online Adaptation in Robotics - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Frontiers in Robotics and AI Year : 2020

Adaptive Prior Selection for Repertoire-based Online Adaptation in Robotics


Repertoire-based learning is a data-efficient adaptation approach based on a two-step process in which (1) a large and diverse set of policies is learned in simulation, and (2) a planning or learning algorithm chooses the most appropriate policies according to the current situation (e.g., a damaged robot, a new object, etc.). In this paper, we relax the assumption of previous works that a single repertoire is enough for adaptation. Instead, we generate repertoires for many different situations (e.g., with a missing leg, on different floors, etc.) and let our algorithm selects the most useful prior. Our main contribution is an algorithm, APROL (Adaptive Prior selection for Repertoire-based Online Learning) to plan the next action by incorporating these priors when the robot has no information about the current situation. We evaluate APROL on two simulated tasks: (1) pushing unknown objects of various shapes and sizes with a robotic arm and (2) a goal reaching task with a damaged hexapod robot. We compare with "Reset-free Trial and Error" (RTE) and various single repertoire-based base-lines. The results show that APROL solves both the tasks in less interaction time than the baselines. Additionally , we demonstrate APROL on a real, damaged hexapod that quickly learns to pick compensatory policies to reach a goal by avoiding obstacles in the path.
Fichier principal
Vignette du fichier
1907.07029.pdf (1.81 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02462935 , version 1 (31-01-2020)
hal-02462935 , version 2 (05-03-2020)
hal-02462935 , version 3 (13-03-2020)



Rituraj Kaushik, Pierre Desreumaux, Jean-Baptiste Mouret. Adaptive Prior Selection for Repertoire-based Online Adaptation in Robotics. Frontiers in Robotics and AI, 2020, 6, ⟨10.3389/frobt.2019.00151⟩. ⟨hal-02462935v3⟩
144 View
137 Download



Gmail Facebook X LinkedIn More