按年被提到
20242025 · 2 次2026
强化学习与智能体›进化策略与探索·arXiv:2402.10877 · cs.AI

Robust agents learn causal world models

Jonathan Richens, Tom Everitt · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2025-03-13 · 最近 2025-06-10
2不同的人
2活跃月份
2讨论串
13被引(OpenAlex)
arXiv 摘要(候选层不写导读)

It has long been hypothesised that causal reasoning plays a fundamental role in robust and general intelligence. However, it is not known if agents must learn causal models in order to generalise to new domains, or if other inductive biases are sufficient. We answer this question, showing that any agent capable of satisfying a regret bound under a large set of distributional shifts must have learned an approximate causal model of the data generating process, which converges to the true causal model for optimal agents. We discuss the implications of this result for several research areas including transfer learning and causal inference.

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

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)

讨论串里没有 ≥100 字的评论,只有提交记录。

被提交为 story · 2 次