On Planning while Learning
S. Safra, M. Tennenholtz
Abstract
This paper introduces a framework for Planning while Learning where an agent is given a goal to achieve in an environment whose behavior is only partially known to the agent. We discuss the tractability of various plan-design processes. We show that for a large natural class of Planning while Learning systems, a plan can be presented and verified in a reasonable time. However, coming up algorithmically with a plan, even for simple classes of systems is apparently intractable. We emphasize the role of off-line plan-design processes, and show that, in most natural cases, the verification (projection) part can be carried out in an efficient algorithmic manner.
Create a lesson
Related papers
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
Liyan Tang, Cyrus Rashtchian, Chun-Sung Ferng et al.
Mechanistic Reaction Prediction via Discrete Flow Matching on Graph-Structured Electron Occupation
Nguyen Xuan-Vu, Octavian Susanu, Daniel Armstrong et al.
Learning a Continuous Sepsis Severity Score Without Hour-by-Hour Supervision: A Two-Site Retrospective Study
Kevin Zhu, Ryan Zhang, Baraa Abed et al.
CorporateBench: Large-Scale Q&A Benchmarking with Temporal Knowledge Bases
Sil Hamilton, Albert Yu Sun, Oscar J. Romero et al.
Sophistication in GenAI Use: Field Evidence from a Large Firm
Nicholas J. Hallman, Zachary T. Kowaleski, Anu Puvvada et al.
Not All Eval-Awareness Is Equal: Capabilities Framing Predicts Compliance
Allison Zhuang, Santiago Aranguri