Abstract
Computer models can be used to investigate the role of emotion in learning. Here we present EARL, our framework for the systematic study of the relation between emotion, adaptation and reinforcement learning (RL). EARL enables the study of, among other things, communicated affect as reinforcement to the robot; the focus of this chapter. In humans, emotions are crucial to learning. For example, a parent—observing a child—uses emotional expression to encourage or discourage specific behaviors. Emotional expression can therefore be a reinforcement signal to a child. We hypothesize that affective facial expressions facilitate robot learning, and compare a social setting with a non-social one to test this. The non-social setting consists of a simulated robot that learns to solve a typical RL task in a continuous grid-world environment. The social setting additionally consists of a human (parent) observing the simulated robot (child). The human’s emotional expressions are analyzed in real time and converted to an additional reinforcement signal used by the robot; positive expressions result in reward, negative expressions in punishment. We quantitatively show that the “social robot” indeed learns to solve its task significantly faster than its “non-social sibling”. We conclude that this presents strong evidence for the potential benefit of affective communication with humans in the reinforcement learning loop.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ashby, F.G., Isen, A.M., Turken, U.: A Neuro-psychological theory of positive affect and its influence on cognition. Psychological Review 106(3), 529–550 (1999)
Avila-Garcia, O., Cañamero, L.: Using hormonal feedback to modulate action selection in a competitive scenario. In: From Animals to Animats 8: Proc. 8th Intl. Conf. on Simulation of Adaptive Behavior, pp. 243–252. MIT Press, Cambridge (2004)
Belavkin, R.V.: On relation between emotion and entropy. In: Proc. of the AISB’04 Symposium on Emotion, Cognition and Affective Computing, pp. 1–8. AISB Press (2004)
Berridge, K.C.: Pleasures of the brain. Brain and Cognition 52, 106–128 (2003)
Blanchard, A.J., Cañamero, L.: Modulation of exploratory behavior for adaptation to the context. In: Proc. of the AISB’06 Symposium on Biologically Inspired Robotics (Biro-net), pp. 131–137. AISB Press (2006)
Botelho, L.M., Coelho, H.: Information processing, motivation and decision making. In: Proc. 4th International Workshop on Artificial Intelligence in Economics and Management (1998)
Breazeal, C.: Affective interaction between humans and robots. In: Kelemen, J., Sosík, P. (eds.) ECAL 2001. LNCS (LNAI), vol. 2159, pp. 582–591. Springer, Heidelberg (2001)
Breazeal, C., Brooks, R.: Robot emotion: A functional perspective. In: Fellous, J.-M., Arbib, M. (eds.) Who needs emotions: The brain meets the robot, pp. 271–310. Oxford University Press, Oxford (2004)
Breazeal, C., Scassellati, B.: Robots that imitate humans. Trends in Cognitive Sciences 6(11), 481–487 (2002)
Breazeal, C., Velasquez, J.: Toward teaching a robot ‘infant’ using emotive communication acts. In: Edmonds, B., Dautenhahn, K. (eds.) Socially Situated Intelligence: a workshop held at SAB’98, Zürich. University of Zürich Technical Report, pp. 25–40 (1998)
Broekens, J., Kosters, W.A., Verbeek, F.J.: On emotion, anticipation and adaptation: Investigating the potential of affect-controlled selection of anticipatory simulation in artificial adaptive agents. In press (2007)
Cañamero, D.: Designing emotions for activity selection. Dept. of Computer Science Technical Report DAIMI PB 545. University of Aarhus, Denmark (2000)
Charman, T., Baird, G.: Practitioner review: Diagnosis of autism spectrum disorder in 2- and 3-year-old children. Journal of Child Psychology and Psychiatry 43(3), 289–305 (2002)
Clore, G.L., Gasper, K.: Feeling is believing: Some affective influences on belief. In: Frijda, N., Manstead, A.S.R., Bem, S. (eds.) Emotions and Beliefs, pp. 10–44. Cambridge Univ. Press, Cambridge (2000)
Cos-Aguilera, I., et al.: Ecological integration of affordances and drives for behaviour selection. In: Proc. of the Workshop on Modeling Natural Action Selection, pp. 225–228. AISB Press (2005)
Custers, R., Aarts, H.: Positive affect as implicit motivator: On the nonconscious operation of behavioral goals. Journal of Personality and Social Psychology 89(2), 129–142 (2005)
Damasio, A.R.: Descartes’ error. Penguin, New York (1994)
Doya, K.: Metalearning and neuromodulation. Neural Networks 15(4), 495–506 (2002)
Dreisbach, G., Goschke, K.: How positive affect modulates cognitive control: Reduced perseveration at the cost of increased distractibility. Journal of Experimental Psychology: Learning, Memory, and Cognition 30(2), 343–353 (2004)
Fong, T., Nourbakhsh, I., Dautenhahn, K.: A survey of socially interactive robots. Robots and Autonomous Systems 42, 143–166 (2003)
Forgas, J.P.: Feeling is believing? The role of processing strategies in mediating affective influences in beliefs. In: Frijda, N., Manstead, A.S.R., Bem, S. (eds.) Emotions and Beliefs, pp. 108–143. Cambridge University Press, Cambridge (2000)
Frijda, N.H., Mesquita, B.: Beliefs through Emotions. In: Frijda, N., Manstead, A.S.R., Bem, S. (eds.) Emotions and Beliefs, pp. 45–77. Cambridge University Press, Cambridge (2000)
Frijda, N.H., Manstead, A.S.R., Bem, S.: The influence of emotions on beliefs. In: Frijda, N., Manstead, A.S.R., Bem, S. (eds.) Emotions and Beliefs, pp. 1–9. Cambridge University Press, Cambridge (2000)
Gandanho, S.C.: Learning behavior-selection by emotions and cognition in a multi-goal robot task. Journal of Machine Learning Research 4, 385–412 (2003)
Gasper, K., Clore, L.G.: Attending to the big picture: Mood and global versus local processing of visual information. Psychological Science 13(1), 34–40 (2002)
Isbell Jr., C.L., et al.: A social reinforcement learning agent. In: Proceedings of the fifth international conference on Autonomous agents, pp. 377–384. ACM Press, New York (2001)
Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: A survey. Journal of Artificial Intelligence Research 4, 237–285 (1996)
Lin, L.J.: Reinforcement learning for robots using neural networks. Doctoral dissertation. Carnegie Mellon University, Pittsburgh (1993)
Mehrabian, A.: Basic Dimensions for a General Psychological Theory. OG&H Publishers, Cambridge (1980)
Mitsunaga, N., et al.: Robot behavior adaptation for human-robot interaction based on policy gradient reinforcement learning. In: Proc. Of the International Conference on Intelligent Robots and Systems (IROS), pp. 218–225. IEEE Computer Society Press, Los Alamitos (2005)
Thrun, S., et al.: A tour-guide robot that learns. In: Burgard, W., Christaller, T., Cremers, A.B. (eds.) KI 1999. LNCS (LNAI), vol. 1701, pp. 14–26. Springer, Heidelberg (1999)
Pantic, M., et al.: Human computing and machine understanding of human behavior: A Survey. In: Proc. ACM Int’l Conf. Multimodal Interfaces, pp. 239–248 (2006)
Pantic, M., Rothkranz, L.J.M.: Automatic analysis of facial expressions: The state of the art. IEEE Transactions on Pattern Analysis and Machine Intelligence 22(12), 1424–1445 (2000)
Papudesi, V.N., Huber, M.: Learning from reinforcement and advice using composite reward functions. In: Proc. Of the 16th International FLAIR Conference, pp. 361–365. AAAI Press, Menlo Park (2003)
Papudesi, V.N., Huber, M.: Interactive refinement of control policies for autonomous robots. In: Proc. of the 10th IASTED International Conference on Robotics and Applications, Honolulu HI, IASTED (2004)
Picard, R.W.: Affective Computing. MIT Press, Cambridge (1997)
Picard, R.W., et al.: Affective learning — A manifesto. BT Technology Journal 22(4), 253–269 (2004)
Rolls, E.T.: Précis of The brain and emotion. Behavioral and Brain Sciences 23, 177–191 (2000)
Russell, J.A.: Core affect and the psychological construction of emotion. Psychological Review 110(1), 145–172 (2003)
Scherer, K.R.: Appraisal considered as a process of multilevel sequential checking. In: Scherer, K.R., Schorr, A., Johnstone, T. (eds.) Appraisal processes in emotion: Theory, Methods, Research, pp. 92–120. Oxford Univ. Press, New York (2001)
Sutton, R., Barto, A.: Reinforcement learning: An introduction. MIT Press, Cambridge (1998)
Ogata, T., Sugano, S., Tani, J.: Open-end human robot interaction from the dynamical systems perspective: Mutual adaptation and incremental learning. In: Orchard, B., Yang, C., Ali, M. (eds.) IEA/AIE 2004. LNCS (LNAI), vol. 3029, pp. 435–444. Springer, Heidelberg (2004)
Thomaz, A.L., Breazeal, C.: Teachable characters: User studies, design principles, and learning performance. In: Gratch, J., et al. (eds.) IVA 2006. LNCS (LNAI), vol. 4133, pp. 395–406. Springer, Heidelberg (2006)
Thomaz, A.L., Breazeal, C.: Reinforcement learning with human teachers: Evidence of feedback and guidance with implications for learning performance. In: Proc. of the 21st National Conference on Artificial Intelligence, AAAI Press, Menlo Park (2006b)
Thomaz, A.L., Hoffman, G., Breazeal, C.: Real-time interactive reinforcement learning for robots. In: Proc. of AAAI Workshop on Human Comprehensible Machine Learning, Pittsburgh, PA (2005)
Velasquez, J.D.: A computational framework for emotion-based control. In: SAB’98 Workshop on Grounding Emotions in Adaptive Systems (1998)
Wright, I.: Reinforcement learning and animat emotions. In: From Animals to Animats 4: Proc. of the 4th International Conference on the Simulation of Adaptive Behavior (SAB), pp. 272–284. MIT Press, Cambridge (1996)
OpenCV: http://www.intel.com/technology/computing/opencv/index.htm
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Broekens, J. (2007). Emotion and Reinforcement: Affective Facial Expressions Facilitate Robot Learning. In: Huang, T.S., Nijholt, A., Pantic, M., Pentland, A. (eds) Artifical Intelligence for Human Computing. Lecture Notes in Computer Science(), vol 4451. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-72348-6_6
Download citation
DOI: https://doi.org/10.1007/978-3-540-72348-6_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-72346-2
Online ISBN: 978-3-540-72348-6
eBook Packages: Computer ScienceComputer Science (R0)