Online Learning with Stochastic Recurrent Neural Networks using Intrinsic Motivation Signals

Daniel Tanneberg, Jan Peters, Elmar Rueckert
Proceedings of the 1st Annual Conference on Robot Learning, PMLR 78:167-174, 2017.

Abstract

Continuous online adaptation is an essential ability for the vision of fully autonomous and lifelong-learning robots. Robots need to be able to adapt to changing environments and constraints while this adaption should be performed without interrupting the robot’s motion. In this paper, we introduce a framework for probabilistic online motion planning and learning based on a bio-inspired stochastic recurrent neural network. Furthermore, we show that the model can adapt online and sample-efficiently using intrinsic motivation signals and a mental replay strategy. This fast adaptation behavior allows the robot to learn from only a small number of physical interactions and is a promising feature for reusing the model in different environments. We evaluate the online planning with a realistic dynamic simulation of the KUKA LWR robotic arm. The efficient online adaptation is shown in simulation by learning an unknown workspace constraint using mental replay and \textitcognitive dissonance as intrinsic motivation signal.

Cite this Paper


BibTeX
@InProceedings{pmlr-v78-tanneberg17a, title = {Online Learning with Stochastic Recurrent Neural Networks using Intrinsic Motivation Signals}, author = {Tanneberg, Daniel and Peters, Jan and Rueckert, Elmar}, booktitle = {Proceedings of the 1st Annual Conference on Robot Learning}, pages = {167--174}, year = {2017}, editor = {Levine, Sergey and Vanhoucke, Vincent and Goldberg, Ken}, volume = {78}, series = {Proceedings of Machine Learning Research}, month = {13--15 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v78/tanneberg17a/tanneberg17a.pdf}, url = {https://proceedings.mlr.press/v78/tanneberg17a.html}, abstract = {Continuous online adaptation is an essential ability for the vision of fully autonomous and lifelong-learning robots. Robots need to be able to adapt to changing environments and constraints while this adaption should be performed without interrupting the robot’s motion. In this paper, we introduce a framework for probabilistic online motion planning and learning based on a bio-inspired stochastic recurrent neural network. Furthermore, we show that the model can adapt online and sample-efficiently using intrinsic motivation signals and a mental replay strategy. This fast adaptation behavior allows the robot to learn from only a small number of physical interactions and is a promising feature for reusing the model in different environments. We evaluate the online planning with a realistic dynamic simulation of the KUKA LWR robotic arm. The efficient online adaptation is shown in simulation by learning an unknown workspace constraint using mental replay and \textitcognitive dissonance as intrinsic motivation signal. } }
Endnote
%0 Conference Paper %T Online Learning with Stochastic Recurrent Neural Networks using Intrinsic Motivation Signals %A Daniel Tanneberg %A Jan Peters %A Elmar Rueckert %B Proceedings of the 1st Annual Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2017 %E Sergey Levine %E Vincent Vanhoucke %E Ken Goldberg %F pmlr-v78-tanneberg17a %I PMLR %P 167--174 %U https://proceedings.mlr.press/v78/tanneberg17a.html %V 78 %X Continuous online adaptation is an essential ability for the vision of fully autonomous and lifelong-learning robots. Robots need to be able to adapt to changing environments and constraints while this adaption should be performed without interrupting the robot’s motion. In this paper, we introduce a framework for probabilistic online motion planning and learning based on a bio-inspired stochastic recurrent neural network. Furthermore, we show that the model can adapt online and sample-efficiently using intrinsic motivation signals and a mental replay strategy. This fast adaptation behavior allows the robot to learn from only a small number of physical interactions and is a promising feature for reusing the model in different environments. We evaluate the online planning with a realistic dynamic simulation of the KUKA LWR robotic arm. The efficient online adaptation is shown in simulation by learning an unknown workspace constraint using mental replay and \textitcognitive dissonance as intrinsic motivation signal.
APA
Tanneberg, D., Peters, J. & Rueckert, E.. (2017). Online Learning with Stochastic Recurrent Neural Networks using Intrinsic Motivation Signals. Proceedings of the 1st Annual Conference on Robot Learning, in Proceedings of Machine Learning Research 78:167-174 Available from https://proceedings.mlr.press/v78/tanneberg17a.html.

Related Material