Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machines
| Autor: | Kumar, Sreejan, Correa, Carlos G., Dasgupta, Ishita, Marjieh, Raja, Hu, Michael Y., Hawkins, Robert D., Daw, Nathaniel D., Cohen, Jonathan D., Narasimhan, Karthik, Griffiths, Thomas L. |
|---|---|
| Rok vydání: | 2022 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | Strong inductive biases give humans the ability to quickly learn to perform a variety of tasks. Although meta-learning is a method to endow neural networks with useful inductive biases, agents trained by meta-learning may sometimes acquire very different strategies from humans. We show that co-training these agents on predicting representations from natural language task descriptions and programs induced to generate such tasks guides them toward more human-like inductive biases. Human-generated language descriptions and program induction models that add new learned primitives both contain abstract concepts that can compress description length. Co-training on these representations result in more human-like behavior in downstream meta-reinforcement learning agents than less abstract controls (synthetic language descriptions, program induction without learned primitives), suggesting that the abstraction supported by these representations is key. Comment: In Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS 2022), winner of Outstanding Paper Award |
| Databáze: | arXiv |
| Externí odkaz: |
|