Developing End-to-End Control Policies for Robotic Swarms Using Deep Q-learning (CROSBI ID 269180)
Prilog u časopisu | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Wei, Yufei ; Nie, Xiaotong ; Hiraga, Motoaki ; Ohkura, Kazuhiro ; Car, Zlatan
engleski
Developing End-to-End Control Policies for Robotic Swarms Using Deep Q-learning
In this study, the use of a popular deep reinforcement learning algorithm – deep Q- learning – in developing end-to-end control policies for robotic swarms is explored. Robots only have limited local sensory capabilities ; however, in a swarm, they can accomplish collective tasks beyond the capability of a single robot. Compared with most automatic design approaches proposed so far, which belong to the field of evolutionary robotics, deep reinforcement learning techniques provide two advantages: (i) they enable researchers to develop control policies in an end-to-end fashion ; and (ii) they require fewer computation resources, especially when the control policy to be developed has a large parameter space. The proposed approach is evaluated in a round-trip task, where the robots are required to travel between two destinations as much as possible. Simulation results show that the proposed approach can learn control policies directly from high- dimensional raw camera pixel inputs for robotic swarms.
swarm robotics, automatic design, deep reinforcement learning, deep Q-learning
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o izdanju
23 (5)
2019.
920-927
objavljeno
1343-0130
10.20965/jaciii.2019.p0920
Povezanost rada
Elektrotehnika, Računarstvo, Strojarstvo