按年被提到
20212021 · 2 次2026
AI 安全、伦理与社会影响›通用智能与意识·arXiv:2102.12321 · cs.AI

AGENT: A Benchmark for Core Psychological Reasoning

Tianmin Shu, Abhishek Bhandwaldar, Chuang Gan, Kevin A. Smith, Shari Liu, Dan Gutfreund, Elizabeth Spelke, Joshua B. Tenenbaum, Tomer D. Ullman · 2021
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2021-07-20 · 最近 2021-10-10
2不同的人
2活跃月份
2讨论串
36被引(OpenAlex)
arXiv 摘要(候选层不写导读)

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.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论throwawaybutwhy · 2021-10

“https://arxiv.org/abs/2102.12321 It's frustrating to have to wade through journalistic crap and blog spam and blog post before getting to the real paper. For humanity's sake, it's in the first line of my comment (BLUF and all that).”

IBM Research creates new benchmark for measuring AI原评论 ↗
被提交为 story · 1 次