AGENT: A Benchmark for Core Psychological Reasoning

02/24/2021
by   Tianmin Shu, et al.
9

For machine agents to successfully interact with humans in real-world settings, they will need to develop an understanding of human mental life. Intuitive psychology, the ability to reason about hidden mental variables that drive observable actions, comes naturally to people: even pre-verbal infants can tell agents from objects, expecting agents to act efficiently to achieve goals given constraints. Despite recent interest in machine agents that reason about other agents, it is not clear if such agents learn or hold the core psychology principles that drive human reasoning. Inspired by cognitive development studies on intuitive psychology, we present a benchmark consisting of a large dataset of procedurally generated 3D animations, AGENT (Action, Goal, Efficiency, coNstraint, uTility), structured around four scenarios (goal preferences, action efficiency, unobserved constraints, and cost-reward trade-offs) that probe key concepts of core intuitive psychology. We validate AGENT with human-ratings, propose an evaluation protocol emphasizing generalization, and compare two strong baselines built on Bayesian inverse planning and a Theory of Mind neural network. Our results suggest that to pass the designed tests of core intuitive psychology at human levels, a model must acquire or have built-in representations of how agents plan, combining utility computations and core knowledge of objects and physics.

READ FULL TEXT

page 4

page 5

page 8

research
06/25/2023

The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling Probabilistic Social Inferences from Linguistic Inputs

Human beings are social creatures. We routinely reason about other agent...
research
02/23/2021

Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others

To achieve human-like common sense about everyday life, machine learning...
research
03/26/2020

Too many cooks: Coordinating multi-agent collaboration through inverse planning

Collaboration requires agents to coordinate their behavior on the fly, s...
research
08/04/2022

Solving the Baby Intuitions Benchmark with a Hierarchically Bayesian Theory of Mind

To facilitate the development of new models to bridge the gap between ma...
research
03/12/2021

Towards Socially Intelligent Agents with Mental State Transition and Human Utility

Building a socially intelligent agent involves many challenges, one of w...
research
10/04/2022

Type theory in human-like learning and inference

Humans can generate reasonable answers to novel queries (Schulz, 2012): ...
research
04/05/2018

Human Intention Recognition in Flexible Robotized Warehouses based on Markov Decision Processes

The rapid growth of e-commerce increases the need for larger warehouses ...

Please sign up or login with your details

Forgot password? Click here to reset