technical paper

AAAI 2024

February 24, 2024

Vancouver , Canada

Neural Reasoning about Agents’ Goals, Preferences, and Actions


intuitive psychology

theory of mind

deep learning

We propose the Intuitive Reasoning Network (IRENE) - a novel neural model for intuitive psychological reasoning about agents' goals, preferences, and actions that can generalise previous experiences to new situations. IRENE combines a graph neural network for learning agent and world state representations with a transformer to encode the task context. When evaluated on the challenging Baby Intuitions Benchmark, IRENE achieves new state-of-the-art performance on three out of its five tasks - with up to 48.9% improvement. In contrast to existing methods, IRENE is able to bind preferences to specific agents, to better distinguish between rational and irrational agents, and to better understand the role of blocking obstacles. We also investigate, for the first time, the influence of the training tasks on test performance. Our analyses demonstrate the effectiveness of IRENE in combining prior knowledge gained during training for unseen evaluation tasks.


SlidesPaperTranscript English (automatic)

Next from AAAI 2024

Learning Uncertainty-Aware Temporally-Extended Actions
technical paper

Learning Uncertainty-Aware Temporally-Extended Actions

AAAI 2024

+1Min-hwan OhJoongkyu Lee
Joongkyu Lee and 3 other authors

24 February 2024

Stay up to date with the latest Underline news!

Select topic of interest (you can select more than one)


  • All Lectures
  • For Librarians
  • Resource Center
  • Free Trial
Underline Science, Inc.
1216 Broadway, 2nd Floor, New York, NY 10001, USA

© 2023 Underline - All rights reserved