NovelGym: A Flexible Ecosystem for Hybrid Planning and Learning Agents Designed for Open Worlds

Autor:	Goel, Shivam, Wei, Yichen, Lymperopoulos, Panagiotis, Chura, Klara, Scheutz, Matthias, Sinapov, Jivko
Rok vydání:	2024
Předmět:	Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	As AI agents leave the lab and venture into the real world as autonomous vehicles, delivery robots, and cooking robots, it is increasingly necessary to design and comprehensively evaluate algorithms that tackle the ``open-world''. To this end, we introduce NovelGym, a flexible and adaptable ecosystem designed to simulate gridworld environments, serving as a robust platform for benchmarking reinforcement learning (RL) and hybrid planning and learning agents in open-world contexts. The modular architecture of NovelGym facilitates rapid creation and modification of task environments, including multi-agent scenarios, with multiple environment transformations, thus providing a dynamic testbed for researchers to develop open-world AI agents. Comment: Accepted at AAMAS-2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2401.03546 Zobrazit plný text záznamu View this record from Arxiv