Abstract
Improving sample efficiency of Reinforcement Learning (RL) in sparse-reward environments poses a significant challenge. In scenarios where the reward structure is complex, accurate action evaluation often relies heavily on precise information about past achieved subtasks and their order. Previous approaches have often failed or proved inefficient in constructing and leveraging such intricate reward structures. In this work, we propose an RL algorithm that can automatically structure the reward function for sample efficiency, given a set of labels that signify subtasks. Given such minimal knowledge about the task, we train a high-level policy that selects optimal subtasks in each state together with a low-level policy that efficiently learns to complete each sub-task. We evaluate our algorithm in a variety of sparse-reward environments. The experiment results show that our method significantly outperforms the state-of-art baselines as the difficulty of the task increases.
Original language | English |
---|---|
Title of host publication | ECAI 2024 - 27th European Conference on Artificial Intelligence, Including 13th Conference on Prestigious Applications of Intelligent Systems, PAIS 2024, Proceedings |
Editors | Ulle Endriss, Francisco S. Melo, Kerstin Bach, Alberto Bugarin-Diz, Jose M. Alonso-Moral, Senen Barro, Fredrik Heintz |
Publisher | IOS Press |
Pages | 2282-2289 |
Number of pages | 8 |
ISBN (Electronic) | 9781643685489 |
DOIs | |
Publication status | Published - 16 Oct 2024 |
Event | 27th European Conference on Artificial Intelligence, ECAI 2024 - Santiago de Compostela, Spain Duration: 19 Oct 2024 → 24 Oct 2024 |
Publication series
Name | Frontiers in Artificial Intelligence and Applications |
---|---|
Volume | 392 |
ISSN (Print) | 0922-6389 |
ISSN (Electronic) | 1879-8314 |
Conference
Conference | 27th European Conference on Artificial Intelligence, ECAI 2024 |
---|---|
Country/Territory | Spain |
City | Santiago de Compostela |
Period | 19/10/24 → 24/10/24 |
Bibliographical note
Publisher Copyright:© 2024 The Authors.