RETRACTED ARTICLE: Neuromodulation of internal emergent representations for sequential tasks

Serotonin and dopamine transmitters are synthesized in the lower brain but are transmitted widely to many areas of the brain for diffused use. Emergent representations are critical for understanding their effects. In prior work Zheng et al. (in: Proceedings of 2013 international joint conference on neural networks (IJCNN2013), pp 1404–1411, Dallas, Texas, USA, August 4–9, 2013), their effects on internal, non-motor neurons were studied for only pattern recognition tasks. In this paper, we study their effects on sequential tasks—robot navigation under different settings. They are sequential tasks because the outcome of behavior depends on not only the current behavior as in pattern recognition but also the previous behaviors and environment (e.g., previous navigational trajectories). Analytically, we show that the serotonin and dopamine systems affect the performance of sequential tasks in a compound way. Experimentally, we show that the effect on the learning rate of internal feature neurons (in the Y area) allows the agent to approach a friend and avoid an enemy faster as compounding effects of sequential states in static and dynamic environment. Further, we test the effect of punishment and reward schedule with the same initial locations. These simulation experiments all indicate that the reinforcement learning via the serotonin and dopamine systems is beneficial for developing desirable behaviors in this set of sequential tasks—staying statistically close to its friend and away from its enemy. As far as we know, this is the first work that investigates the effects of reinforcer (via serotonin and dopamine) on internal neurons (Y neurons) for sequential tasks using emergent representations.

[1]  Jeffrey L. Krichmar,et al.  The Neuromodulatory System: A Framework for Survival and Adaptive Behavior in a Challenging World , 2008, Adapt. Behav..

[2]  Alice C. Parker,et al.  Synaptic Variability in a Cortical Neuromorphic Circuit , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[3]  Pierre-Yves Oudeyer,et al.  Intrinsic Motivation Systems for Autonomous Mental Development , 2007, IEEE Transactions on Evolutionary Computation.

[4]  Juyang Weng,et al.  Modulation for emergent networks: serotonin and dopamine. , 2013, Neural networks : the official journal of the International Neural Network Society.

[5]  Jekanthan Thangavelautham,et al.  Tackling Learning Intractability Through Topological Organization and Regulation of Cortical Networks , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[6]  Manfred Hild,et al.  Proposal of an Intrinsically Motivated System for Exploration of Sensorimotor State Spaces , 2010, EpiRob.

[7]  Francesco Mannella,et al.  Intrinsically motivated action-outcome learning and goal-based action recall: a system-level bio-constrained computational model. , 2013, Neural networks : the official journal of the International Neural Network Society.

[8]  Jeffrey L. Krichmar,et al.  Model of the interactions between neuromodulators and prefrontal cortex during a resource allocation task , 2012, 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL).

[9]  Sham M. Kakade,et al.  Opponent interactions between serotonin and dopamine , 2002, Neural Networks.

[10]  Juyang Weng,et al.  Symbolic Models and Emergent Models: A Review , 2012, IEEE Transactions on Autonomous Mental Development.

[11]  M. Paradiso,et al.  Neuroscience: Exploring the brain, 3rd ed. , 2007 .

[12]  Antonios Gasteratos,et al.  Robot navigation in large-scale social maps: An action recognition approach , 2016, Expert Syst. Appl..

[13]  Juyang Weng,et al.  Modeling dopamine and serotonin systems in a visual recognition network , 2011, The 2011 International Joint Conference on Neural Networks.

[14]  Andrey V. Savkin,et al.  A method of reactive 3D navigation for a tight surface scan by a nonholonomic mobile robot , 2017, Autom..

[15]  Lee Spector,et al.  Genetic Programming for Reward Function Search , 2010, IEEE Transactions on Autonomous Mental Development.

[16]  Kathryn E. Merrick,et al.  A Comparative Study of Value Systems for Self-Motivated Exploration and Learning by Robots , 2010, IEEE Transactions on Autonomous Mental Development.

[17]  Moussa Haddad,et al.  A hybrid approach for autonomous navigation of mobile robots in partially-known environments , 2016, Robotics Auton. Syst..

[18]  Peter Dayan,et al.  Dopamine: generalization and bonuses , 2002, Neural Networks.

[19]  Jeffrey L. Krichmar,et al.  Neuromodulation as a robot controller , 2009, IEEE Robotics & Automation Magazine.

[20]  Zhengping Ji,et al.  A Biologically-Motivated Developmental System Towards Perceptual Awareness in Vehicle-Based Robots , 2007 .

[21]  Juyang Weng,et al.  Neuromorphic motivated systems , 2011, The 2011 International Joint Conference on Neural Networks.

[22]  Rüdiger Dillmann,et al.  Autonomous navigation for reconfigurable snake-like robots in challenging, unknown environments , 2017, Robotics Auton. Syst..

[23]  John K. Tsotsos,et al.  Robot navigation via spatial and temporal coherent semantic maps , 2016, Eng. Appl. Artif. Intell..

[24]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[25]  Kui Qian,et al.  Modeling the effects of neuromodulation on internal brain areas: Serotonin and dopamine , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[26]  Nabil Derbel,et al.  Fuzzy logic controllers design for omnidirectional mobile robot navigation , 2016, Appl. Soft Comput..

[27]  Richard L. Lewis,et al.  Intrinsically Motivated Reinforcement Learning: An Evolutionary Perspective , 2010, IEEE Transactions on Autonomous Mental Development.

[28]  Juyang Weng,et al.  Dually Optimal Neuronal Layers: Lobe Component Analysis , 2009, IEEE Transactions on Autonomous Mental Development.

[29]  Heiko Wersing,et al.  A Biologically Motivated System for Unconstrained Online Learning of Visual Objects , 2006, ICANN.

[30]  Kyungjae Lee,et al.  Real-time nonparametric reactive navigation of mobile robots in dynamic environments , 2017, Robotics Auton. Syst..

[31]  Sebastiano Cavallaro,et al.  Genomic analysis of serotonin receptors in learning and memory , 2008, Behavioural Brain Research.

[32]  James A. Reggia,et al.  Symbolic Representation of Recurrent Neural Network Dynamics , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[33]  Jeffrey L. Krichmar,et al.  as a Robot Controller Neuromodulation as a Robot Controller A Brain-Inspired Strategy for Controlling Autonomous Robots , 2009 .

[34]  Jeffrey L. Krichmar,et al.  Effect of neuromodulation on performance in game playing: A modeling study , 2010, 2010 IEEE 9th International Conference on Development and Learning.