arXiv Open Access 2020

Intrinsic Robotic Introspection: Learning Internal States From Neuron Activations

Nikos Pitsillos Ameya Pore Bjorn Sand Jensen Gerardo Aragon-Camarasa
Lihat Sumber

Abstrak

We present an introspective framework inspired by the process of how humans perform introspection. Our working assumption is that neural network activations encode information, and building internal states from these activations can improve the performance of an actor-critic model. We perform experiments where we first train a Variational Autoencoder model to reconstruct the activations of a feature extraction network and use the latent space to improve the performance of an actor-critic when deciding which low-level robotic behaviour to execute. We show that internal states reduce the number of episodes needed by about 1300 episodes while training an actor-critic, denoting faster convergence to get a high success value while completing a robotic task.

Topik & Kata Kunci

Penulis (4)

N

Nikos Pitsillos

A

Ameya Pore

B

Bjorn Sand Jensen

G

Gerardo Aragon-Camarasa

Format Sitasi

Pitsillos, N., Pore, A., Jensen, B.S., Aragon-Camarasa, G. (2020). Intrinsic Robotic Introspection: Learning Internal States From Neuron Activations. https://arxiv.org/abs/2011.01880

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2020
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓