Klink, Pascal (2023)
Generalization and Transferability in Reinforcement Learning.
Technische Universität Darmstadt
doi: 10.26083/tuprints-00024717
Master Thesis, Primary publication, Publisher's Version
Text
pascal_thesis.pdf Copyright Information: CC BY 4.0 International - Creative Commons, Attribution. Download (1MB) |
Item Type: | Master Thesis | ||||
---|---|---|---|---|---|
Type of entry: | Primary publication | ||||
Title: | Generalization and Transferability in Reinforcement Learning | ||||
Language: | English | ||||
Date: | 17 October 2023 | ||||
Place of Publication: | Darmstadt | ||||
Collation: | iii, 54 Seiten | ||||
DOI: | 10.26083/tuprints-00024717 | ||||
Abstract: | Reinforcement learning has proven capable of extending the applicability of machine learning to domains in which knowledge cannot be acquired from labeled examples but only via trial-and-error. Being able to solve problems with such characteristics is a crucial requirement for autonomous agents that can accomplish tasks without human intervention. However, most reinforcement learning algorithms are designed to solve exactly one task, not offering means to systematically reuse previous knowledge acquired in other problems. Motivated by insights from homotopic continuation methods, in this work we investigate approaches based on optimization- and concurrent systems theory to gain an understanding of conceptual and technical challenges of knowledge transfer in reinforcement learning domains. Building upon these findings, we present an algorithm based on contextual relative entropy policy search that allows an agent to generate a structured sequence of learning tasks that guide its learning towards a target distribution of tasks by giving it control over an otherwise hidden context distribution. The presented algorithm is evaluated on a number of robotic tasks, in which a desired system state needs to be reached, demonstrating that the proposed learning scheme helps to increase and stabilize learning performance. |
||||
Alternative Abstract: |
|
||||
Status: | Publisher's Version | ||||
URN: | urn:nbn:de:tuda-tuprints-247171 | ||||
Classification DDC: | 000 Generalities, computers, information > 004 Computer science | ||||
Divisions: | 20 Department of Computer Science > Intelligent Autonomous Systems | ||||
TU-Projects: | EC/H2020|640554|SKILLS4ROBOTS | ||||
Date Deposited: | 17 Oct 2023 11:39 | ||||
Last Modified: | 13 Dec 2023 12:05 | ||||
URI: | https://tuprints.ulb.tu-darmstadt.de/id/eprint/24717 | ||||
PPN: | 513212191 | ||||
Export: |
View Item |