Research Topic

Information Theory and the Sensori-Motor Loop

The field of Embodied Artificial Intelligence highlights the significance of embodiment and situatedness. Agents sense and act within the sensori-motor loop, which defines the context of learning including their morphology. The development of cognitive capabilities cannot be understood detached from this context. In this project, we study the way in which learning principles for embodied agents shape behavioural patterns that reflect morphology and environmental constraints. Particular behaviours of interest are exploration and body coordination. The ultimate goal of the project is to develop an information-theoretic understanding of the sensori-motor loop. Causal aspects, such as causal effects of acting on sensing, and their role in the context of autonomy and control play a central role to this end.


Further Information:


inJournal
2020 Journal Open Access
David C. Krakauer, Nils Bertschinger, Eckehard Olbrich, Jessica C. Flack and Nihat Ay

The information theory of individuality

In: Theory in biosciences, 139 (2020) 2, pp. 209-223
inBook
2019 Repository Open Access
Nihat Ay, Johannes Rauh and Guido Montúfar

A continuity result for optimal memoryless planning in POMDPs

In: RLDM 2019 : 4th multidisciplinary conference on reinforcement learning and decision making ; July 7-10, 2019 ; Montréal, Canada
Montréal, Canada : University, 2019. - pp. 362-365
Academic
2019 Repository Open Access
Sacha Sokoloski

Implementing Bayesian inference with neural networks

Dissertation, Universität Leipzig, 2019
Book
2019
Keyan Ghazi-Zahedi

Morphological intelligence : measuring the body's contribution to intelligence

Cham : Springer, 2019. - xiii, 180
ISBN: 978-3-030-20620-8, ISBN: 978-3-030-20621-5
inBook
2019 Repository Open Access
Guido Montúfar, Johannes Rauh and Nihat Ay

Task-agnostic constraining in average reward POMDPs

In: Task-agnostic reinforcement learning : workshop at ICLR, 06 May 2019, New Orleans
[S. L.] : ICLR, 2019.
inJournal
2017 Journal Open Access
Keyan Ghazi-Zahedi, Carlotta Langer and Nihat Ay

Morphological computation : synergy of body and brain

In: Entropy, 19 (2017) 9, p. 456
Academic
2018
Keyan Ghazi-Zahedi

Morphological intelligence : information-theoretic quantifications of the morphological contribution to intelligence

Habilitation, Universität Leipzig, 2018
inJournal
2021 Repository Open Access
Santiago Muiños-Landin, Keyan Ghazi-Zahedi and Frank Cichos

Reinforcement learning of artificial microswimmers

In: Science robotics, 6 (2021) 52, eabd9285
inBook
2018 Repository Open Access
Guido Montúfar, Johannes Rauh and Nihat Ay

Uncertainty and stochasticity of optimal policies

In: Proceedings of the 11th workshop on uncertainty processing WUPES '18, June 6-9, 2018 / Václav Kratochvíl (ed.)
Praha : MatfyzPress, 2018. - pp. 133-140
inBook
2017 Repository Open Access
Keyan Ghazi-Zahedi, Raphael Deimel, Guido Montúfar, Vincent Wall and Oliver Brock

Morphological computation : the good, the bad, and the ugly

In: 2017 IEEE/RSJ international conference on intelligent robots and systems (IROS) : Vancouver, BC, Canada ; September 24-28, 2017
New York, NY : IEEE, 2017. - pp. 464-469
Preprint
2017 Repository Open Access
Keyan Ghazi-Zahedi

NMODE - Neuro-MODule evolution

inJournal
2017 Journal Open Access
Ralf Der and Georg Martius

Self-organized behavior generation for musculoskeletal robots

In: Frontiers in neurorobotics, 11 (2017), p. 8
inBook
2017
Guido Montúfar, Keyan Ghazi-Zahedi and Nihat Ay

Stochasticity of optimal policies for POMDPs

In: RLDM 2017 : 3rd multidisciplinary conference on reinforcement learning and decision making ; June 11-14, 2017 ; Ann Arbor, Michigan, USA
Michigan : University, 2017. - T97
inBook
2016
Georg Martius, Rafael Hostettler, Alois Knoll and Ralf Der

Compliant control for soft robots : emergent behavior of a tendon driven anthropomorphic arm

In: 2016 IEEE/RSJ international conference on intelligent robots and systems (IROS) : October 9-14 2016 ; Daejeon, Korea
New York, NY : IEEE, 2016. - pp. 767-773
inJournal
2016 Journal Open Access
Keyan Ghazi-Zahedi, Daniel F. B. Haeufle, Guido Montúfar, Syn Schmitt and Nihat Ay

Evaluating morphological computation in muscle and DC-motor driven models of hopping movements

In: Frontiers in robotics and AI, 3 (2016), p. 42
inJournal
2016 Journal Open Access
Ralf Der

In search for the neural mechanisms of individual development : behavior-driven differential Hebbian learning

In: Frontiers in robotics and AI, 2 (2016), p. 37
Preprint
2016 Repository Open Access
Guido Montúfar, Keyan Ghazi-Zahedi and Nihat Ay

Information theoretically aided reinforcement learning for embodied agents

inJournal
2015 Journal Open Access
Guido Montúfar, Keyan Ghazi-Zahedi and Nihat Ay

A theory of cheap control in embodied systems

In: PLoS computational biology, 11 (2015) 9, e1004427
Academic
2015 Repository Open Access
Holger Bernigau

Causal models over infinite graphs and their application to the sensorimotor loop : general stochastic aspects and gradient methods for optimal control

Dissertation, Universität Leipzig, 2015
inJournal
2015 Repository Open Access
Ralf Der and Georg Martius

Novel plasticity rule can explain the development of sensorimotor intelligence

In: Proceedings of the National Academy of Sciences of the United States of America, 112 (2015) 45, E6224-E6232
inBook
2015 Repository Open Access
Keyan Ghazi-Zahedi and Johannes Rauh

Quantifying morphological computation based on an information decomposition of the sensorimotor loop

In: Proceedings of the european conference on artificial life 2015, ECAL 2015 / Paul Andrews... (eds.)
Cambridge, MA : MIT Press, 2015. - pp. 70-77
inJournal
2015 Repository Open Access
Nihat Ay and Wolfgang Löhr

The Umwelt of an embodied agent : a measure-theoretic definition

In: Theory in biosciences, 134 (2015) 3-4, pp. 105-116
inBook
2014
Nihat Ay and Keyan Ghazi-Zahedi

On the causal structure of the sensorimotor loop

In: Guided self-organization : inception / Mikhail Prokopenko (ed.)
Berlin [u. a.] : Springer, 2014. - pp. 261-294
(Emergence, complexity, and computation)
inBook
2014
Mikhail Prokopenko, Daniel Polani and Nihat Ay

On the cross-disciplinary nature of guided self-organisation

In: Guided self-organization : inception / Mikhail Prokopenko (ed.)
Berlin [u. a.] : Springer, 2014. - pp. 3-15
(Emergence, complexity, and computation)
inBook
2014
Ralf Der

On the role of embodiment for self-organizing robots : behavior as broken symmetry

In: Guided self-organization : inception / Mikhail Prokopenko (ed.)
Berlin [u. a.] : Springer, 2014. - pp. 193-221
(Emergence, complexity, and computation)
inBook
2014
Georg Martius, Ralf Der and J. Michael Herrmann

Robot learning by guided self-organization

In: Guided self-organization : inception / Mikhail Prokopenko (ed.)
Berlin [u. a.] : Springer, 2014. - pp. 223-260
(Emergence, complexity, and computation)
inBook
2014 Repository Open Access
Georg Martius, Luisa Jahn, Helmut Hauser and Verena V. Hafner

Self-exploration of the Stumpy robot with predictive information maximization

In: From Animals to Animats 13 : 13th International Conference on Simulation of Adaptive Behavior, SAB 2014, Castellón, Spain, July 22-25, 2014 ; proceedings / Angel P. Del Pobil... (eds.)
New York [u.a.] : Springer, 2014. - pp. 32-42
(Lecture notes in computer science ; 8575)
Preprint
2013
Nihat Ay and Wolfgang Löhr

A measure-theoretic description of the intrinsic view of embodied agents

inBook
2013 Journal Open Access
Ralf Der and Georg Martius

Behavior as broken symmetry in embodied self-organizing robots

In: Advances in artificial life, ECAL 2013 : proceedings of the twelfth european conference on the synthesis and simulation of living systems / Pietro Lió... (eds.)
Cambridge, MA : MIT Press, 2013. - pp. 601-608
inBook
2013 Repository Open Access
Nihat Ay and Keyan Ghazi-Zahedi

Causal effects for prediction and deliberative decision making of embodied systems

In: Advances in cognitive neurodynamics III : proceedings of the 3rd International Conference on Cognitive Neurodynamics 2011 ; [June 9-13, 2011, Hilton Niseko Village, Hokkaido, Japan] / Yoko Yamaguchi (ed.)
Dordrecht : Springer, 2013. - pp. 499-506
(Advances in cognitive neurodynamics)
inJournal
2013 Journal Open Access
Georg Martius, Ralf Der and Nihat Ay

Information driven self-organization of complex robotic behaviors

In: PLOS ONE, 8 (2013) 5, e63400
inJournal
2013 Journal Open Access
Keyan Ghazi-Zahedi, Georg Martius and Nihat Ay

Linear combination of one-step predictive information with an external reward in an episodic policy gradient setting : a critical analysis

In: Frontiers in psychology, 4 (2013), p. 801
inJournal
2013 Journal Open Access
Keyan Ghazi-Zahedi and Nihat Ay

Quantifying morphological computation

In: Entropy, 15 (2013) 5, pp. 1887-1915
inJournal
2012 Journal Open Access
Nihat Ay, Ralf Der and Mikhail Prokopenko

Guided self-organization : perception-action loops of embodied systems

In: Theory in biosciences, 131 (2012) 3, pp. 125-127
inJournal
2012
Nihat Ay, Holger Bernigau, Ralf Der and Mikhail Prokopenko

Information-driven self-organization : the dynamical system approach to autonomous robot behavior

In: Theory in biosciences, 131 (2012) 3, pp. 161-179
Book
2011
Ralf Der and Georg Martius

The playful machine : theoretical foundation and practical realization of self-organizing robots

Berlin : Springer, 2011. - XIII, 333
(Cognitive systems monographs ; 15)
ISBN: 978-3-642-20253-7, ISBN: 978-3-642-20252-0
inJournal
2010 Repository Open Access
Keyan Ghazi-Zahedi, Nihat Ay and Ralf Der

Higher coordination with less control : a result of information maximization in the sensorimotor loop

In: Adaptive behavior, 18 (2010) 3/4, pp. 338-355
inBook
2010
Frank Güttler, Wolfgang Rabe, Jörn Hoffmann, Martin Bogdan and Ralf Der

Transposing simulated self-organizing robots into reality using the plug and learn architecture

In: Proceedings of the International Conference on Fuzzy Computation and International Conference on Neural Computation : Valencia, Spain, October 24 - 26, 2010
[Setuball] : SciTePress - Science and Techn. Publ., 2010. - pp. 350-357
inBook
2008
Ralf Der, Frank Güttler and Nihat Ay

Predictive information and emergent cooperativity in a chain of mobile robots

In: Artificial Life XI : Proceedings of the Eleventh International Conference on the Simulation and Synthesis of Living Systems
Cambridge, MA : MIT Press, 2008. - pp. 166-172
inJournal
2008 Journal Open Access
Nihat Ay, Nils Bertschinger, Ralf Der, Frank Güttler and Eckehard Olbrich

Predictive information and explorative behavior of autonomous robots

In: The European physical journal / B, 63 (2008) 3, pp. 329-339
inBook
2008
Keyan Ghazi-Zahedi, Arndt von Twickel and Frank Pasemann

YARS : A physical 3D simulator for evolving controllers for real robots

In: Simulation, modeling, and programming for autonomous robots : first international conference, SIMPSR 2008 Venice, Italy, November 3-7, 2008 proceedings / Stefano Carpin... (eds.)
New York : Springer, 2008. - pp. 75-86
(Lecture notes in artificial intelligence ; 5325)
inBook
2007
Keyan Ghazi-Zahedi and Frank Pasemann

Adaptive behavior control by self-regulating neurons

In: 50 years of artificial intelligence : essays dedicated to the 50th aniversary of artificial intelligence / Max Lungarella... (eds.)
Berlin : Springer, 2007. - pp. 196-205
(Lecture notes in computer science ; 4850 : Lecture notes in artificial intelligence)
inBook
1999 Repository Open Access
Frank Pasemann, Ulrich Steinmetz and Ralf Der

Homeokinesis : a new principle to back up evolution with learning

In: Computational Intelligence for Modelling, Control and Automation / Masoud Mohammadian (ed.)
Amsterdam [u.a.] : IOS Press, 1999. - pp. 43-47
(Concurrent Systems Engineering Series ; 55)