2000 character limit reached
Balancing utility and cognitive cost in social representation (2310.04852v2)
Published 7 Oct 2023 in cs.AI
Abstract: To successfully navigate its environment, an agent must construct and maintain representations of the other agents that it encounters. Such representations are useful for many tasks, but they are not without cost. As a result, agents must make decisions regarding how much information they choose to store about the agents in their environment. Using selective social learning as an example task, we motivate the problem of finding agent representations that optimally trade off between downstream utility and information cost, and illustrate two example approaches to resource-constrained social representation.
- State abstraction as compression in apprenticeship learning. In AAAI Conference on Artificial Intelligence, 2019. URL https://api.semanticscholar.org/CorpusID:53689696.
- Bayesian reinforcement learning with limited cognitive load. ArXiv, abs/2305.03263, 2023. URL https://api.semanticscholar.org/CorpusID:258546889.
- Rational quantitative attribution of beliefs, desires and percepts in human mentalizing. Nature Human Behaviour, 1(4):1–10, 2017.
- Resource-rational decision making. Current Opinion in Behavioral Sciences, 41:15–21, 2021.
- Elements of information theory / Thomas M. Cover, Joy A. Thomas. Wiley-Interscience, Hoboken, N.J, second edition. edition, 2006. ISBN 0471241954.
- K. Craik. Hypothesis on the nature of thought, 1943.
- D. C. Dennett. The intentional stance. 1987. URL https://api.semanticscholar.org/CorpusID:143977161.
- C. Heyes. Who knows? metacognitive social learning strategies. Trends in Cognitive Sciences, 20:204–213, 2016.
- The origins of social categorization. Trends in Cognitive Sciences, 21:556–568, 2017.
- F. Lieder and T. L. Griffiths. Resource-rational analysis: Understanding human cognition as the optimal use of limited computational resources. Behavioral and Brain Sciences, 43, 2019.
- B. F. Malle. Chapter 12 - the fundamental tools, and possibly universals, of human social cognition. In R. M. Sorrentino and S. Yamaguchi, editors, Handbook of Motivation and Cognition Across Cultures, pages 267–296. Academic Press, San Diego, 2008. ISBN 978-0-12-373694-9. doi:https://doi.org/10.1016/B978-0-12-373694-9.00012-X. URL https://www.sciencedirect.com/science/article/pii/B978012373694900012X.
- M. L. Puterman. Markov Decision Processes: Discrete Stochastic Dynamic Programming. John Wiley & Sons, Inc., 1st edition, 1994. ISBN 0471619779.
- Gaussian processes for machine learning / Carl Edward Rasmussen, Christopher K.I. Williams. Adaptive computation and machine learning. MIT Press, Cambridge, Mass. ;, 2006. ISBN 026218253X.
- Cognitive culture: theoretical and empirical insights into social learning strategies. Trends in Cognitive Sciences, 15:68–76, 2011.
- M. Rhodes and A. S. Baron. The development of social categorization. Annual review of developmental psychology, 1:359–386, 2019.
- Reinforcement Learning: An Introduction. Adaptive Computation and Machine Learning series. MIT Press, Cambridge, 1998.
- Reinforcement Learning: An Introduction. The MIT Press, second edition, 2018. URL http://incompleteideas.net/book/the-book-2nd.html.
- E. C. Tolman. Cognitive maps in rats and men. Psychological review, 55 4:189–208, 1948. URL https://api.semanticscholar.org/CorpusID:42496633.
- Orbitofrontal cortex as a cognitive map of task space. Neuron, 81:267–279, 2014. URL https://api.semanticscholar.org/CorpusID:2713112.
- Social learning with a grain of salt. In Proceedings of the Annual Meeting of the Cognitive Science Society, volume 45, 2023.
- Generalization guides human exploration in vast decision spaces. Nature Human Behaviour, 2:915–924, 2018. URL https://api.semanticscholar.org/CorpusID:53278852.