Intrinsic motivation and mental replay enable efficient online adaptation in stochastic recurrent networks. (January 2019)

• Record Type: Journal Article
• Authors: Tanneberg, Daniel; Peters, Jan; Rueckert, Elmar
• Is Part Of: Neural networks. Volume 109(2019)
• Page Start: 67
• Page End: 80
• Publication Date: 2019-01
• Subjects: Intrinsic motivation -- Online learning -- Experience replay -- Autonomous robots -- Spiking recurrent networks -- Neural sampling; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2018.10.005
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Autonomous robots need to interact with unknown, unstructured and changing environments, constantly facing novel challenges. Therefore, continuous online adaptation for lifelong-learning and the need of sample-efficient mechanisms to adapt to changes in the environment, the constraints, the tasks, or the robot itself are crucial. In this work, we propose a novel framework for probabilistic online motion planning with online adaptation based on a bio-inspired stochastic recurrent neural network. By using learning signals which mimic the intrinsic motivation signal cognitive dissonance in addition with a mental replay strategy to intensify experiences, the stochastic recurrent network can learn from few physical interactions and adapts to novel environments in seconds. We evaluate our online planning and adaptation framework on an anthropomorphic KUKA LWR arm. The rapid online adaptation is shown by learning unknown workspace constraints sample-efficiently from few physical interactions while following given way points.