Acquiring reusable skills in intrinsically motivated reinforcement learning

Marzieh Davoodabadi Farahani () and Nasser Mozayani ()
Additional contact information
Marzieh Davoodabadi Farahani: Iran University of Science and Technology
Nasser Mozayani: Iran University of Science and Technology

Journal of Intelligent Manufacturing, 2021, vol. 32, issue 8, No 5, 2147-2168

Abstract: Abstract This paper proposes a novel incremental model for acquiring skills and using them in Intrinsically Motivated Reinforcement Learning (IMRL). In this model, the learning process is divided into two phases. In the first phase, the agent explores the environment and acquires task-independent skills by using different intrinsic motivation mechanisms. We present two intrinsic motivation factors for acquiring skills by detecting states that can lead to other states (being a cause) and by detecting states that help the agent to transition to a different region (discounted relative novelty). In the second phase, the agent evaluates the acquired skills to find suitable ones for accomplishing a specific task. Despite the importance of assessing task-independent skills to perform a task, the idea of evaluating skills and pruning them has not been considered in IMRL literature. In this article, two methods are presented for evaluating previously learned skills based on the value function of the assigned task. Using such a two-phase learning model and the skill evaluation capability helps the agent to acquire task-independent skills that can be transferred to other similar tasks. Experimental results in four domains show that the proposed method significantly increases learning speed.

Keywords: Hierarchical reinforcement learning; Skill; Option; Intrinsic motivation; Skill evaluation (search for similar items in EconPapers)
Date: 2021
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10845-020-01629-3 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joinma:v:32:y:2021:i:8:d:10.1007_s10845-020-01629-3

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10845

DOI: 10.1007/s10845-020-01629-3

Access Statistics for this article

Journal of Intelligent Manufacturing is currently edited by Andrew Kusiak

More articles in Journal of Intelligent Manufacturing from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().