Till sidans topp

Sidansvarig: Webbredaktion
Sidan uppdaterades: 2012-09-11 15:12

Tipsa en vän
Utskriftsversion

Improving Robot Motor Lea… - Göteborgs universitet Till startsida
Webbkarta
Till innehåll Läs mer om hur kakor används på gu.se

Improving Robot Motor Learning with Negatively Valenced Reinforcement Signals

Artikel i vetenskaplig tidskrift
Författare N. Navarro-Guerrero
Robert Lowe
S. Wermter
M. A. Y. Automation
Publicerad i Frontiers in Neurorobotics
Volym 11
Sidor 1-14
ISSN 1662-5218
Publiceringsår 2017
Publicerad vid Institutionen för tillämpad informationsteknologi (GU)
Sidor 1-14
Språk en
Länkar dx.doi.org/10.3389/fnbot.2017.00010
Ämnesord reinforcement learning, inverse kinematics, nociception, punishment, self-protective mechanisms, neural activity, punishment, reward, dynamics, models, Computer Science, Robotics, Neurosciences & Neurology
Ämneskategorier Data- och informationsvetenskap

Sammanfattning

Both nociception and punishment signals have been used in robotics. However, the potential for using these negatively valenced types of reinforcement learning signals for robot learning has not been exploited in detail yet. Nociceptive signals are primarily used as triggers of preprogrammed action sequences. Punishment signals are typically disembodied, i. e., with no or little relation to the agent-intrinsic limitations, and they are often used to impose behavioral constraints. Here, we provide an alternative approach for nociceptive signals as drivers of learning rather than simple triggers of preprogrammed behavior. Explicitly, we use nociception to expand the state space while we use punishment as a negative reinforcement learning signal. We compare the performance-in terms of task error, the amount of perceived nociception, and length of learned action sequences-of different neural networks imbued with punishment-based reinforcement signals for inverse kinematic learning. We contrast the performance of a version of the neural network that receives nociceptive inputs to that without such a process. Furthermore, we provide evidence that nociception can improve learning-making the algorithm more robust against network initializations-as well as behavioral performance by reducing the task error, perceived nociception, and length of learned action sequences. Moreover, we provide evidence that punishment, at least as typically used within reinforcement learning applications, may be detrimental in all relevant metrics.

Sidansvarig: Webbredaktion|Sidan uppdaterades: 2012-09-11
Dela:

På Göteborgs universitet använder vi kakor (cookies) för att webbplatsen ska fungera på ett bra sätt för dig. Genom att surfa vidare godkänner du att vi använder kakor.  Vad är kakor?