Work

Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer

Year: 2019

Type: conference-paper

Abstract: We focus on the problem of teaching a robot to solve tasks presented sequentially, i.e., in a continual learning scenario. The robot should be able to solve all tasks it has encountered, without forgetting past tasks. We provide preliminary work on applying Reinforcement Learning to such setting, on 2D navigation tasks for a 3 wheel omni-directional robot. Our approach takes advantage of state representation learning and policy distillation. Policies are trained using learned features as input, rather than raw observations, allowing better sample efficiency. Policy distillation is used to combine multiple policies into a single one that solves all encountered tasks.

Source: HAL

DOI: 10.48550/arxiv.1906.04452

Authors: Traoré, René, Caselles-Dupré, Hugo, Lesort, Timothée, Sun, Te, Díaz-Rodríguez, Natalia, Filliat, David

Institutions: Institut national de recherche en sciences et technologies du numérique, École Nationale Supérieure de Techniques Avancées, Thales (France), École Nationale Supérieure de Techniques Avancées Paris

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Quality education

Open Access status: green

OpenAlex ID: W4297740831

FWCI: 1.173

Cites: 39

Cited by: 26

Related to: 10