NovelGym: A Flexible Ecosystem for Hybrid Planning and Learning Agents Designed for Open Worlds
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909218564472832 |
|---|---|
| author | Goel, Shivam Wei, Yichen Lymperopoulos, Panagiotis Chura, Klara Scheutz, Matthias Sinapov, Jivko |
| author_facet | Goel, Shivam Wei, Yichen Lymperopoulos, Panagiotis Chura, Klara Scheutz, Matthias Sinapov, Jivko |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_03546 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | NovelGym: A Flexible Ecosystem for Hybrid Planning and Learning Agents Designed for Open Worlds Goel, Shivam Wei, Yichen Lymperopoulos, Panagiotis Chura, Klara Scheutz, Matthias Sinapov, Jivko Artificial Intelligence 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. |
| title | NovelGym: A Flexible Ecosystem for Hybrid Planning and Learning Agents Designed for Open Worlds |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2401.03546 |