Výsledky vyhledávání

Report

NL2Plan: Robust LLM-Driven Planning from Minimal Text Descriptions

Autor: Gestrin, Elliot, Kuhlmann, Marco, Seipp, Jendrik

Today's classical planners are powerful, but modeling input tasks in formats such as PDDL is tedious and error-prone. In contrast, planning with Large Language Models (LLMs) allows for almost any input text, but offers no guarantees on plan quality o

Externí odkaz: http://arxiv.org/abs/2405.04215

Zobrazit plný text záznamu

Report

Numeric Reward Machines

Autor: Levina, Kristina, Pappas, Nikolaos, Karapantelakis, Athanasios, Feljan, Aneta Vulgarakis, Seipp, Jendrik

Reward machines inform reinforcement learning agents about the reward structure of the environment and often drastically speed up the learning process. However, reward machines only accept Boolean features such as robot-reached-gold. Consequently, ma

Externí odkaz: http://arxiv.org/abs/2404.19370

Zobrazit plný text záznamu

Report

Consolidating LAMA with Best-First Width Search

Autor: Corrêa, Augusto B., Seipp, Jendrik

One key decision for heuristic search algorithms is how to balance exploration and exploitation. In classical planning, novelty search has come out as the most successful approach in this respect. The idea is to favor states that contain previously u

Externí odkaz: http://arxiv.org/abs/2404.17648

Zobrazit plný text záznamu