skip to main content
survey

Competence Awareness for Humans and Machines: A Survey and Future Research Directions from Psychology

Published: 07 October 2024 Publication History

Abstract

Machine learning researchers are beginning to understand the need for machines to be able to self-assess their competence and express it in a human understandable form. However, current machine learning algorithms do not yet have the range or complexity of competence awareness measures present in humans. This review first describes progress towards competence awareness in machines, and then examines the psychology literature on competence awareness and competence motivation to identify the limitations of current competence awareness algorithms. The article concludes with a discussion of the necessary and promising future research directions for creating competence-aware machines.

References

[1]
S. Thrun and T. Mitchell. 1995. Lifelong robot learning. Robotics and Autonomous Systems 15, 1-2 (1995), 25–46.
[2]
T. Lesort, V. Lomonaco, A. Stoian, D. Maltoni, D. Filliat, and N. Diaz Rodriguez. 2020. Continual learning for robotics: Definition, framework, learning strategies, opportunities and challenges. Information Fusion 58 (2020), 52–68.
[3]
D. Isele. 2018. Lifelong Reinforcement Learning on Mobile Robots. Ph.D. Dissertation. University of Pennsylvania.
[4]
P. Dhakan, K. Merrick, N. Siddique, and I. Rano. 2019. Open-ended continuous learning of compound goals. IEEE Transactions on Cognitive and Developmental Systems 13, 2 (2019), 274–285.
[5]
V. G. Santucci, P.-Y. Oudeyer, A. G. Barto, and G. Baldassarre. 2020. Editorial: Intrinsically motivated open-ened learning in autonomous robots. Frontiers in Neurorobotics 13 (2020), 115.
[6]
D. Silver, Q. Yang, and L. Li. 2013. Lifelong machine learning systems: Beyond learning algorithms. In Proceedings of the AAAI Spring Symposium.
[7]
D. Weitekamp, E. Harpstead, and K. Koedinger. 2020. An interaction design for machine teaching to develop AI tutors. In Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems.
[8]
V. G. Santucci, G. Baldassarre, and M. Mirolli. 2013. Which is the best intrinsic motivation signal for learning multiple skills? Frontiers in Neurorobotics 7 (2013), 1–22.
[9]
C. Tessler, S. Givony, T. Zahavy, D. Mankowitz, and S. Mannor. 2017. A deep hierarchical approach to lifelong learning in minecraft. In Proceedings of the AAAI Conference on Artificial Intelligence.
[10]
A. Logacjov, M. Kerzel, and S. Wermter. 2021. Learning then, learning now, and every second in between: Lifelong learning with a simulated humanoid robot (in English). Frontiers in Neurorobotics 15, 78 (2021), 669534. DOI:
[11]
G. Parisi, R. Kemker, J. Part, C. Kanan, and S. Wermter. 2019. Continual lifelong learning with neural networks: A review. Neural Networks 113 (2019), 54–71.
[12]
Y. Ding, W. Jiang, and Q. Lou. 2020. Hardware design and the competency awareness of a neural network. Nature Electronics 3 (2020), 514–523.
[13]
T. Devries and G. Taylor. 2018. Leveraging uncertainty estimates for predicting segmentation quality. arXiv preprint arXiv:1807.00502 (2018).
[14]
D. Hendrycks and K. Gimpel. 2017. A baseline for detecting misclassified and out-of-distribution examples in neural networks. In Proceedings of the International Conference on Learning Representations.
[15]
Y. Gal and Z. Ghahramani. 2016. Dropout in a Bayesian approximation: Representing model uncertainty in deep learning. In Proceedings of the International Conference on Machine Learning.
[16]
N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. 2014. Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research 15, 1 (2014), 1929–1958.
[17]
B. Lakshminarayanan, A. Pritzel, and C. Blundell. 2017. Simple and scalable predictive uncertainty estimation using deep ensembles. In Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS’17).
[18]
J. Shane and J. Heckhausen. 2019. Motivational theory of lifespan development. In Work across the Lifespan, B. Baltes, C. Rudolph, and H. Zacher (Eds.). Elsevier, 111–133.
[19]
J. Heckhausen and H. Heckhausen. 2018. Development of motivation. In Motivation and Action. Springer, 679–743.
[20]
J. Field. 2000. Lifelong Learning and the New Educational Order. Trentham Books.
[21]
G. Martin. 2011. Understanding Motivation for Lifelong Education, through Biography, Complexity and Control. Ph.D. Dissertation. School of Education, University of Birmingham.
[22]
J. Heckhausen. 2000. Evolutionary perspectives on human motivation. American Behavioral Scientist 43 (2000), 1015–1029.
[23]
S. Dehaene, H. Lau, and S. Kouider. 2017. What is consciousness and could machines have it? Science 385 (2017), 486–492.
[24]
J. Weng, J. McClelland, A. Pentland, O. Sporns, I. Stockman, M. Sur, and E. Thelen. 2001. Artificial intelligence: Autonomous mental development by robots and animals. Science 291 (2001), 599–600.
[25]
P.-Y. Oudeyer, F. Kaplan, and V. Hafner. 2007. Intrinsic motivation systems for autonomous mental development. IEEE Transactions on Evolutionary Computation 11, 2 (2007), 265–286.
[26]
A. G. Barto, S. Singh, and N. Chentanez. 2004. Intrinsically motivated learning of hierarchical collections of skills. In Proceedings of the International Conference on Developmental Learning. 112–119.
[27]
S. Singh, A. G. Barto, and N. Chentanez. 2005. Intrinsically motivated reinforcement learning. Advances in Neural Information Processing Systems 17 (2005), 1281–1288.
[28]
K. Merrick and M. L. Maher. 2009. Motivated Reinforcement Learning: Curious Characters for Multuser Games. Springer.
[29]
F. Dignum and R. Conte. 1998. Intentional agents and goal formation. In Proceedings of Intelligent Agents IV: Agent Theories, Architectures, and Languages.
[30]
V. Santucci, G. Baldassare, and M. Mirolli. 2016. GRAIL: A goal-discovering robotic architecture for intrinsically-motivated learning. IEEE Transactions on Cognitive and Developmental Systems 8, 3 (2016), 214–231.
[31]
E. Alpaydin. 2020. Introduction to Machine Learning (4th ed.). MIT Press, Cambridge, MA.
[32]
J. Graham, J. Starzyk, and D. Jachyra. 2015. Opportunistic behavior in motivated learning agents. IEEE Transactions on Neural Networks and Learning Systems 26, 8 (2015), 1735–1746.
[33]
K. Merrick and M. L. Maher. 2009. Motivated Reinforcement Learning: Curious Characters for Multiuser Games, R. Nugent (Ed.). Springer, Berlin, Germany.
[34]
A. Baranes and P.-Y. Oudeyer. 2010. Maturationally-constrained competence-based intrinsically motivated learning. In Proceedings of the IEEE International Conference on Developmental and Learning.
[35]
L. Jacquey, G. Baldassarre, V. G. Santucci, and J. K. O'Regan. 2019. Sensorimotor contingencies as a key drive of development: From babies to robots. Frontiers in Neurorobotics 13 (2019), 98.
[36]
A. G. Barto and S. Mahadevan. 2003. Recent advances in hierarchical reinforcement learning. Discrete Event Dynamic Systems: Theory and Applications 13, 4 (2003), 41–77.
[37]
C. Vigorito and A. G. Barto. 2010. Intrinsically motivated hierarchical skill learning in structured environments. IEEE Transactions on Autonomous Mental Development 2, 2 (2010), 132–142.
[38]
Z. Yang, K. Merrick, and H. Abbass. 2018. Hierarchical deep reinforcement learning for continuous action control. IEEE Transactions on Neural Networks and Learning Systems 29 (2018), 5174–5184.
[39]
R. Sutton, D. Precup, and S. Singh. 1999. A framework for temporal abstraction in reinforcement learning. Artificial Intelligence 112 (1999), 181–211.
[40]
G. Baldassarre. 2022. Intrinsic motivations for open-ended learning. In Cognitive Robots, A. Cangelosi and M. Asada (Eds.). MIT Press, Cambridge, MA.
[41]
J. D. M. Otten, N. Karssemeijer, J. H. C. L. Hendriks, J. H. Groenewoud, J. Fracheboud, A. L. M. Verbeek, H. J. de Koning, and R. Holland. 2005. Effect of recall rate on earlier screen detection of breast cancers based on the Dutch performance indicators. Journal of the National Cancer Institute 97, 10 (2005), 748–754.
[42]
K. Takahashi, K. Yamamoto, A. Kuchiba, and T. Koyama. 2022. Confidence interval for micro-averaged F1 and macro-averaged F1 scores. Applied Intelligence 52, 5 (2022), 4961–4972.
[43]
D. Goldberg. 1989. Genetic Algorithms in Search, Optimisation and Machine Learning. Addison-Wesley Professional, Reading, MA.
[44]
R. Sutton and A. G. Barto. 2014. Reinforcement Learning: An Introduction (2nd ed.). MIT Press, Cambridge, MA.
[45]
H. Nakayama, M. Arakawa, and R. Sasaki. 2001. A computational intelligence approach to optimization with unknown objective functions. In Proceedings of the International Conference on Artificial Neural Networks. 73–80.
[46]
M. Kana. 2020. Uncertainty in deep learning: How to measure? Medium. Retrieved August 28, 2024 from https://towardsdatascience.com/my-deep-learning-model-says-sorry-i-dont-know-the-answer-that-s-absolutely-ok-50ffa562cb0b
[47]
B. A. Cliath. 2000. Learning for Life: White Paper on Adult Education. The Stationery Office.
[48]
L. Rokach. 2010. Ensemble based classifiers. Artificial Intelligence Review 33 (2010), 1–39.
[49]
E. Kreyzig. 2010. Advanced Engineering Mathematics. John Wiley & Sons, New York, NY.
[50]
A. Maharaj, R. Sinha, D. Arbour, I. Waudby-Smith, S. Z. Liu, and M. Sinha. 2023. Anytime-valid confidence sequences in an enterprise A/B testing platform. In Companion Proceedings of the ACM Web Conference 2023. 396–400.
[51]
C. Basich, J. Svegliato, K. Hollins Wray, S. Witwicki, J. Biswas, and S. Zilberstein. 2020. Learning to optimise autonomy in competence-aware systems. In Proceedings of the 19th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS’20).
[52]
C. Guo, G. Pleiss, Y. Sun, and K. Weinberger. 2017. On calibration of modern neural networks. In Proceedings of the 34th International Conference on Machine Learning.
[53]
A. G. Barto. 2013. Intrinsic motivation and reinforcement learning. In Intrinsically Motivated Learning in Natural and Artificial Systems, G. Baldassare and M. Mirolli (Eds.). Springer, 17–47.
[54]
L. Esterle and J. Brown. 2020. The competence awareness window: Knowing what I can and cannot do. In Proceedings of the IEEE International Conference on Autonomic Computing and Self-Organising Systems Companion.
[55]
W. Miller, R. Baker, M. Labrum, K. Petsche, Y. Liu, and A. Wagner. 2015. Automated detection of proactive remediation by teachers in reasoning mind classrooms. In Proceedings of the 5th International Conference on Learning Analytics and Knowledge.
[56]
J. Anderson, C. Boyle, R. Farrell, and B. Reiser. 1987. Cognitive principles in the design of computer tutors. In Modelling Cognition, P. Morris (Ed.). John Wiley & Sons, 93–133.
[57]
J. M. Vaca, J. E. Agudo, and M. Rico. 2012. Adaptive competence-based system in an e-learning platform: Adapting support tasks to students. In Proceedings of the 2012 IEEE 12th International Conference on Advanced Learning Technologies. IEEE, 720–721.
[58]
J. Feng-Shun Lin and D. Kulic. 2014. Online segmentation of human motion for automated rehabilitation exercise analysis. IEEE Transactions on Neural Systems and Rehabilitation Engineering 22, 1 (2014), 168–180.
[59]
W. Zhao. 2016. On automatic assessment of rehabilitation exercises with realtime feedback. In Proceedings of the 2016 IEEE International Conference on Electro Information Technology (EIT’16). IEEE, 376–381.
[60]
B. Cain. 2007. A Review of the Mental Workload Literature. Human System Integration Section, Defence Research and Development, Canada.
[61]
E. Debie, R. F. Rojas, J. Fidock, M. Barlow, K. Kasmarik, S. Anavatti, M. Garratt, and H. A. Abbass. 2019. Multi-modal fusion for objective assessment of cognitive workload: A review. IEEE Transactions on Cybernetics 51, 3 (2019), 1542–1555.
[62]
J. Keller. 2019. Researchers eye competency-awareness and trusted computing in machine learning to link humans and machines. Military+Aerospace Electronics. Retrieved February 21, 2019 from https://www.militaryaerospace.com/computers/article/16722153/researchers-eye-competencyawareness-and-trusted-computing-in-machine-learning-to-link-humans-and-machines
[63]
C. Lebiere, L. M. Blaha, C. K. Fallon, and B. Jefferson. 2021. Adaptive cognitive mechanisms to maintain calibrated trust and reliance in automation. Frontiers in Robotics and AI 8 (2021), 652776.
[64]
R. Parasuraman, T. B. Sheridan, and C. D. Wickens. 2008. Situation awareness, mental workload, and trust in automation: Viable, empirically supported cognitive engineering constructs. Journal of Cognitive Engineering and Decision Making 2, 2 (2008), 140–160.
[65]
C. Y. Wong and G. Seet. 2017. Workload, awareness and automation in multiple-robot supervision. International Journal of Advanced Robotic Systems 14, 3 (2017), 1–16.
[66]
R. Iyer, Y. Li, H. Li, M. Lewis, R. Sundar, and K. Sycara. 2018. Transparency and explanation in deep reinforcement learning neural networks. In Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society. 144–150.
[67]
M. Hutchinson, H. Oh, and W. Chen. 2017. A review of source term estimation methods for atmospheric dispersion events using static or mobile sensors. Information Fusion 36 (2017), 130–148.
[68]
E. Lughofer. 2021. Hybrid active learning for reducing the annotation effort of operators in classification systems. Pattern Recognition 44, 2 (2021), 884–896.
[69]
B. Yang, J.-T. Sun, T. Wang, and Z. Chen. 2009. Effective multi-label active learning for text classification. In Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.
[70]
A. Sintov, A. Kimmel, K. Bekris, and A. Boularis. 2020. Motion planning with competency-aware transition models for underactuated adaptive hands. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA’20).
[71]
A. Baranes and P.-Y. Oudeyer. 2009. R-IAC: Robust intrinsically motivated exploration and active learning. IEEE Transactions on Autonomous Mental Development 1, 3 (2009), 155–169.
[72]
A. Baranes and P.-Y. Oudeyer. 2013. Active learning of inverse models with intrinsically motivated goal exploration in robots. Robotics and Autonomous Systems 61, 1 (2013), 49–73.
[73]
F. Kaplan and P.-Y. Oudeyer. 2003. Motivational principles for visual know-how development. In Proceedings of the 3rd International Workshop on Epigenetic Robotics: Modelling Cognitive Development in Robotic Systems. 73–80.
[74]
P.-Y. Oudeyer and F. Kaplan. 2004. Intelligent adaptive curiosity: A source of self-development. In Proceedings of the 4th International Workshop on Epigenetic Robotics. 127–130.
[75]
K. Merrick and M. L. Maher. 2009. Motivated reinforcement learning from interesting events: Adaptive, multitask learning agents for complex environments. Adaptive Behavior 17, 1 (2009), 7–27.
[76]
S. Marsland, U. Nehmzow, and J. Shapiro. 2000. A real-time novelty detector for a mobile robot. In Proceedings of the European Advanced Robotics Systems Masterclass and Conference (EUREL’00).
[77]
K. Merrick. 2017. Value systems for developmental cognitive robotics: A survey. Cognitive Systems Research 41 (2017), 38–55.
[78]
J. Moore. 2016. What is the sense of agency and why does it matter? Frontiers in Psychology 7 (2016), 1272.
[79]
S. Harter. 1978. Effectance motivation reconsidered: Towards a developmental model. Human Development 21, 1 (1978), 34–64.
[80]
J. Heckhausen and R. Schulz. 1959. A life span theory of control. Psychological Review 102 (1995), 284–304.
[81]
R. W. White. 1959. Motivation reconsidered: The concept of competence. Psychological Review 66 (1959), 297–333.
[82]
A. Wigfield and J. Eccles. 2000. Expectancy-value theory of achievement motivation. Contemporary Educational Psychology 25 (2000), 68–81.
[83]
N. Spreng and G. Turner. 2021. From exploration to exploitation: A shifting mental mode in late life development. Trends in Cognitive Science 25, 12 (2021), 1058–1071.
[84]
D. Stipek and D. Mac Iver. 1989. Developmental change in children's assessment of intellectual competence. Child Development 60, 3 (1989), 521–538.
[85]
L. H. Somerville, S. F. Sasse, M. C. Garrad, A. T. Drysdale, N. A. Akar, C. Insel, and R. C. Wilson. 2017. Charting the expansion of strategic exploratory behavior during adolesence. Journal of Experimental Psychology: General 146, 2 (2017), 155–164.
[86]
H. Andrews, J. M. Grilli, and M. Irish. 2019. A review and reappraisal of the default network in normal aging and dementia. Psychology. Published Online, 2019.
[87]
M. Ben Yehuda. 2019. Agency and Confidence: On the Function of Metacognition in Action. Ph.D. Dissertation. University of Oxford.
[88]
M. Zellner. 1970. Self-esteem, reception and influencability. Journal of Personality and Social Psychology 15, 1 (1970), 87–93.
[89]
M. Rosenberg. 1986. Self-concept from middle childhood through adolesence. In Psychological Perspectives on the Self. Vol. 3. Hillsdale, NJ: Lawrence Erlbaum Associates, Hillsdale, NJ, 107–135.
[90]
L. G. Weil, S. M. Fleming, I. Dumontheil, E. J. Kilford, R. S. Weil, G. Rees, R. J. Dolan, and S.-J. Blakemore. 2013. The development of metacognitive ability in adolescence. Consciousness and Cognition 22, 1 (2013), 264–271.
[91]
E. Palmer, A. David, and S. Fleming. 2014. Effects of age on metacognitive efficiency. Consciousness and Cognition 28 (2014), 151–160.
[92]
S. Harter. 1982. The perceived competence scale for children. Child Development 53, 1 (1982), 87–97.
[93]
A. Rich and T. Gurekis. 2018. The limits of learning: Exploration, generalization, and the development of learning traps. Journal of Experimental Psychology: General 147, 11 (2018), 1553–1570.
[94]
J. Heckhausen. 2018. The motivation of developmental regulation. In Motivation and Action. Springer, 745–781.
[95]
J. Brandstaedter and K. Rothermund. 2002. Intentional self-development: Exploring the interfaces between development, intentionality and the self. In Agency, Motivation, and the Life Course, L. Crockett (Ed.). University of Nebraska Press, 31–75.
[96]
A. Santoro, S. Bartunov, M. Botvinick, D. Wierstra, and T. Lillicrap. 2016. Meta-learning with memory-augmented neural networks. In Proceedings of the 33rd International Conference on Machine Learning.
[97]
K. Merrick. 2012. Intrinsic motivation and introspection in reinforcement learning. IEEE Transactions on Autonomous Mental Development 4, 4 (2012), 315–329.
[98]
S. Rabiee, C. Basich, K. Wray, S. Zilberstein, and J. Biswas. 2022. Competence aware path planning via introspective perception. IEEE Robotics and Automation Letters 7, 2 (2022), 3218–3225.
[99]
M. Marsden, K. McGuinness, J. Antony, H. Wei, M. Redzic, J. Tang, Z. Hu, A. Smeaton, and N. E. O'Connor. 2020. Investigating class-level difficulty factors in multi-label classification problems. In Proceedings of the IEEE International Conference on Multimedia and Expo (ICME’20).
[100]
Y. Benigo, J. Louradour, R. Collabert, and J. Weston. 2009. In Proceedings of the International Conference on Machine Learning.
[101]
M. Khani, K. Kasmarik, S. Abpeikar, and M. Barlow. 2023. Using abstraction graphs to promote exploration in curiosity-inspired intrinsic motivation. In Proceedings of the 15th International Joint Conference on Computational Intelligence.

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Computing Surveys
ACM Computing Surveys  Volume 57, Issue 1
January 2025
984 pages
EISSN:1557-7341
DOI:10.1145/3696794
  • Editors:
  • David Atienza,
  • Michela Milano
Issue’s Table of Contents

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 07 October 2024
Online AM: 23 August 2024
Accepted: 17 August 2024
Revised: 15 August 2024
Received: 23 February 2022
Published in CSUR Volume 57, Issue 1

Check for updates

Author Tags

  1. Competence aware
  2. psychology
  3. machine learning

Qualifiers

  • Survey

Funding Sources

  • Australian Research Council Future Fellowship

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 304
    Total Downloads
  • Downloads (Last 12 months)304
  • Downloads (Last 6 weeks)48
Reflects downloads up to 23 Jan 2025

Other Metrics

Citations

View Options

Login options

Full Access

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Full Text

View this article in Full Text.

Full Text

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media