TY - CHAP A1 - Josifovski, Josip A1 - Malmir, Mohammadhossein A1 - Klarmann, Noah A1 - Žagar, Bare Luka A1 - Navarro-Guerrero, Nicolás A1 - Knoll, Alois T1 - Analysis of Randomization Effects on Sim2Real Transfer in Reinforcement Learning for Robotic Manipulation Tasks T2 - 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Kyoto, Japan N2 - 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 KW - Sim2Real KW - Robotics KW - Reinforcment Learning Y1 - 2022 U6 - https://doi.org/10.1109/IROS47612.2022.9981951 SP - 10193 EP - 10200 ER -