Faster MIL-based Subgoal Identification for Reinforcement Learning by Tuning Fewer Hyperparameters

Creative Commons License

SUNEL S., Çilden E., POLAT F.

ACM Transactions on Autonomous and Adaptive Systems, cilt.19, sa.2, 2024 (SCI-Expanded) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 19 Sayı: 2
  • Basım Tarihi: 2024
  • Doi Numarası: 10.1145/3643852
  • Dergi Adı: ACM Transactions on Autonomous and Adaptive Systems
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Aerospace Database, Applied Science & Technology Source, Communication Abstracts, Compendex, Computer & Applied Sciences, INSPEC, Metadex, Civil Engineering Abstracts
  • Anahtar Kelimeler: diverse density, expectation-maximization, hyperparameter search, multiple instance learning, reinforcement learning, Subgoal identification
  • Orta Doğu Teknik Üniversitesi Adresli: Evet

Özet

Various methods have been proposed in the literature for identifying subgoals in discrete reinforcement learning (RL) tasks. Once subgoals are discovered, task decomposition methods can be employed to improve the learning performance of agents. In this study, we classify prominent subgoal identification methods for discrete RL tasks in the literature into the following three categories: graph-based, statistics-based, and multi-instance learning (MIL)-based. As contributions, first, we introduce a new MIL-based subgoal identification algorithm called EMDD-RL and experimentally compare it with a previous MIL-based method. The previous approach adapts MIL's Diverse Density (DD) algorithm, whereas our method considers Expected-Maximization Diverse Density (EMDD). The advantage of EMDD over DD is that it can yield more accurate results with less computation demand thanks to the expectation-maximization algorithm. EMDD-RL modifies some of the algorithmic steps of EMDD to identify subgoals in discrete RL problems. Second, we evaluate the methods in several RL tasks for the hyperparameter tuning overhead they incur. Third, we propose a new RL problem called key-room and compare the methods for their subgoal identification performances in this new task. Experiment results show that MIL-based subgoal identification methods could be preferred to the algorithms of the other two categories in practice.