Tell me why! Explanations support learning relational and causal structure

By Andrew Kyle Lampinen, Nicholas A. Roy, Ishita Dasgupta, Stephanie C. Y. Chan, Allison C. Tam, James L. McClelland, Chen Yan, Adam Santoro, Neil C. Rabinowitz, Jane X. Wang and 1 more. 2021

51 citations recorded by the source corpus.

Inferring the abstract relational and causal structure of the world is a major challenge for reinforcement-learning (RL) agents. For humans, language--particularly in the form of explanations--plays a considerable role in overcoming this challenge. Here, we show that language can play a similar role for deep RL agents in complex environments. While agents typically struggle to acquire relational and causal knowledge, augmenting their experience by training them to predict language descriptions and explanations can overcome these limitations. We show that language can help agents learn challenging relational tasks, and examine which aspects of language contribute to its benefits. We then show that explanations can help agents to infer not only relational but also causal structure. Language can shape the way that agents to generalize out-of-distribution from ambiguous, causally-confounded training, and explanations even allow agents to learn to perform experimental interventions to identify causal relationships. Our results suggest that language description and explanation may be powerful tools for improving agent learning and generalization.

Subfields: Artificial Intelligence, Cognitive Science & Psychology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cognitive Science & Psychology

Citations in the corpus

Can language models learn from explanations in context? (2022, background): “…tuning models for computer vision (Hendricks et al., 2016; Schramowski et al., 2020; Majumder et al., 2021; Mu et al., 2020), for mathematical problem solving by program induction (Ling et al., 2017), or relational reasoning and reinforcement learning (Andreas et al., 2018; Lampinen et al., 2021).”
Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning (2022, background): “…the more common approach of obtaining post-hoc rationalisation , where the answer produced by the model has no direct dependence on the explanation, since the explanation is produced either in parallel to the answer or after the fact (Cobbe et al., 2021; Lampinen et al., 2021; Saha et al., 2020).”
Contrastive Distillation Is a Sample-Efficient Self-Supervised Loss Policy for Transfer Learning (2022, unknown): “Adding explanation data (similar to self-QA) has been shown to improve few-shot performance via prompt manipulation in language models and for RL agents (Lampinen et al., 2021a; 2022), but has been less clearly connected to transfer learning.”
Vygotskian Autotelic Artificial Intelligence: Language and Culture Internalization for Human-Like AI (2022, background): “126 Note however that this approach is neither embodied, nor autotelic.”