Kısmi gözlemlenebilir takviye öğrenme için dolaysız soyutlama

Date

2015

Author

Çilden, Erkin
Polat, Faruk
Şahin, Coşkun

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

2
views

0
downloads

Cite This

Reinforcement learning defines a prominent family of unsupervised machine learning methods in autonomous agents perspective. Markov decision process model provides a solid formal basis for reinforcement learning algorithms. Temporal abstraction mechanisms can be built on reinforcement learning and significant performance gain can be achieved. If the full observability assumption of Markov decision process model is relaxed, the resulting model is partially observable Markov decision process, which constitutes a more realistic but difficult problem setting. Reinforcement learning research for partial observability focuses on techniques to reduce negative impact of perceptual aliasing and huge state-space. In the broadest sense, these studies can be divided into two categories. Model based approaches assume that the state transition model is available to the agent. In the model free approaches, states are completely hidden from the agent. In this project, we propose methods to generalize a known sequence based automatic temporal abstraction technique –namely, extended sequence tree method– to partial observability. We attack the problem in both model based and model free approaches, showing that our methods accelerate well known representatives of each perspective. Effectiveness of our methods are demonstrated by conducting experimentation on widely accepted benchmark problems.

Subject Keywords

Reinforcement Learning, Partially Observable Markov Decision Process, Temporal Abstraction, Extended Sequence Tree

URI

https://app.trdizin.gov.tr/publication/project/detail/TVRRMU5qYzM
https://hdl.handle.net/11511/49848

Collections

Department of Computer Engineering, Project and Design