Adaptive Social Learning using Theory of Mind
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908448046710784 |
|---|---|
| author | Ying, Lance Truong, Ryan Tenenbaum, Joshua B. Gershman, Samuel J. |
| author_facet | Ying, Lance Truong, Ryan Tenenbaum, Joshua B. Gershman, Samuel J. |
| contents | Social learning is a powerful mechanism through which agents learn about the world from others. However, humans don't always choose to observe others, since social learning can carry time and cognitive resource costs. How do people balance social and non-social learning? In this paper, we propose a rational mentalizing model of the decision to engage in social learning. This model estimates the utility of social learning by reasoning about the other agent's goal and the informativity of their future actions. It then weighs the utility of social learning against the utility of self-exploration (non-social learning). Using a multi-player treasure hunt game, we show that our model can quantitatively capture human trade-offs between social and non-social learning. Furthermore, our results indicate that these two components allow agents to flexibly apply social learning to achieve their goals more efficiently. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_09409 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Adaptive Social Learning using Theory of Mind Ying, Lance Truong, Ryan Tenenbaum, Joshua B. Gershman, Samuel J. Multiagent Systems Social learning is a powerful mechanism through which agents learn about the world from others. However, humans don't always choose to observe others, since social learning can carry time and cognitive resource costs. How do people balance social and non-social learning? In this paper, we propose a rational mentalizing model of the decision to engage in social learning. This model estimates the utility of social learning by reasoning about the other agent's goal and the informativity of their future actions. It then weighs the utility of social learning against the utility of self-exploration (non-social learning). Using a multi-player treasure hunt game, we show that our model can quantitatively capture human trade-offs between social and non-social learning. Furthermore, our results indicate that these two components allow agents to flexibly apply social learning to achieve their goals more efficiently. |
| title | Adaptive Social Learning using Theory of Mind |
| topic | Multiagent Systems |
| url | https://arxiv.org/abs/2507.09409 |