Automatic landmark discovery for learning agents under partial observability


Demir A., Cilden E., Polat F.

KNOWLEDGE ENGINEERING REVIEW, cilt.34, 2019 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Derleme
  • Cilt numarası: 34
  • Basım Tarihi: 2019
  • Doi Numarası: 10.1017/s026988891900002x
  • Dergi Adı: KNOWLEDGE ENGINEERING REVIEW
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Orta Doğu Teknik Üniversitesi Adresli: Evet

Özet

In the reinforcement learning context, a landmark is a compact information which uniquely couples a state, for problems with hidden states. Landmarks are shown to support finding good memoryless policies for Partially Observable Markov Decision Processes (POMDP) which contain at least one landmark. SarsaLandmark, as an adaptation of Sarsa(lambda), is known to promise a better learning performance with the assumption that all landmarks of the problem are known in advance.