LLM-based planning agents commit to plans of different lengths before interacting with a partially observable environment. Some aggressively commit to a long plan based on assumptions about unobserved states, while others conservatively plan only over what they have observed. Both behaviors emerge implicitly in pre-tra...
Cassie Huang, Zhan-Wei Cao, Yeawon Lee et al.· 0 citations
A concept-centric framework for building agents that can learn continually and reason flexibly across multiple domains and offers several advantages, including data efficiency, compositional generalization, continual learning, and zero-shot transfer.
Jia-Yuan Mao, Joshua B. Tenenbaum, Jia-Jun Wu· Communications of the ACM· 14 citations· ⚡1
This work introduces Robot Agentic Programming from Demonstrations (RAPID), which automatically generates, verifies, and refines robot programs, given a single visual human demonstration, using an object-centric relational program representation.
Yu-Yao Liu, Jia-Yuan Mao, David Hsu et al.· arXiv.org· 7 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.