SayCanPay: Heuristic Planning with Large Language Models using Learnable Domain Knowledge
Authors:
- Rishi HazraRHRishi Hazra
- Pedro Zuidberg Dos MartiresPMPedro Zuidberg Dos Martires
- Luc De RaedtLRLuc De Raedt
Preprint
Abstract
Large Language Models (LLMs) have demonstrated impressive planning abilities due to their vast "world knowledge". Yet, obtaining plans that are both feasible (grounded in affordances) and cost-effective (in plan length), remains a challenge, despite recent progress. This contrasts with heuristic planning methods that employ domain knowledge (formalized in action models such as PDDL) and heuristic search to generate feasible, optimal plans. Inspired by this, we propose to combine the power of LLMs and heuristic planning by leveraging the world knowledge of LLMs and the principles of heuristic search. Our approach, SayCanPay, employs LLMs to generate actions (Say) guided by learnable domain knowledge, that evaluates actions' feasibility (Can) and long-term reward/payoff (Pay), and heuristic search to select the best sequence of actions. Our contributions are (1) a novel framing of the LLM planning problem in the context of heuristic planning, (2) integrating grounding and cost-effective elements into the generated plans, and (3) using heuristic search over actions. Our extensive evaluations show that our model surpasses other LLM planning approaches.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Text2Motion: from natural language instructions to feasible plansAutonomous Robots, 2023
- Integrating action knowledge and LLMs for task planning and situation handling in open worldsAutonomous Robots, 2023
- Code as Policies: Language Model Programs for Embodied Control2023
- Reasoning with Language Model is Planning with World Model2023
- The Fast Downward Planning SystemJournal of Artificial Intelligence Research, 2006
- Planning as heuristic searchArtificial Intelligence, 2001
- Planning and acting in partially observable stochastic domainsArtificial Intelligence, 1998