• search hit 17 of 1980
Back to Result List

Analysis of Randomization Effects on Sim2Real Transfer in Reinforcement Learning for Robotic Manipulation Tasks

  • Randomization is currently a widely used approach in Sim2Real transfer for data-driven learning algorithms in robotics. Still, most Sim2Real studies report results for a specific randomization technique and often on a highly customized robotic system, making it difficult to evaluate different randomization approaches systematically. To address this problem, we define an easy-to-reproduce experimental setup for a robotic reach-and-balance manipulator task, which can serve as a benchmark for comparison. We compare four randomization strategies with three randomized parameters both in simulation and on a real robot. Our results show that more randomization helps in Sim2Real transfer, yet it can also harm the ability of the algorithm to find a good policy in simulation. Fully randomized simulations and fine-tuning show differentiated results and translate better to the real robot than the other approaches tested

Export metadata

Additional Services

Search Google Scholar
Metadaten
Author:Josip Josifovski, Mohammadhossein Malmir, Noah Klarmann, Bare Luka Žagar, Nicolás Navarro-Guerrero, Alois Knoll
DOI:https://doi.org/10.1109/IROS47612.2022.9981951
Parent Title (English):2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Kyoto, Japan
Document Type:Conference Proceeding
Language:English
Publication Year:2022
Tag:Reinforcment Learning; Robotics; Sim2Real
Page Number:8
First Page:10193
Last Page:10200
Peer reviewed:Ja
faculties / departments:Fakultät für Wirtschaftsingenieurwesen