Investigating Feedback Types in Reinforcement Learning With Human Feedback

No Thumbnail Available

Files

URL

Journal Title

Journal ISSN

Volume Title

Perustieteiden korkeakoulu | Bachelor's thesis
Electronic archive copy is available locally at the Harald Herlin Learning Centre. The staff of Aalto University has access to the electronic bachelor's theses by logging into Aaltodoc with their personal Aalto user ID. Read more about the availability of the bachelor's theses.
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.

Authors

Date

2024-12-13

Department

Major/Subject

Mcode

SCI3095

Degree programme

Aalto Bachelor’s Programme in Science and Technology

Language

en

Pages

22+3

Series

Abstract

Reinforcement learning (RL) has many applications ranging from video games to aiding in autonomous cars. However, RL has some challenges such as difficulties in defining a reward function in complex environments and inefficient learning. To address these challenges reinforcement learning with human feedback (RLHF) incorporates human knowledge in the feedback process. This thesis aims to analyse and compare common human feedback types by conducting a literature review of key studies and frameworks in RLHF. The feedback types that are discussed include comparative, attribute, scalar, visual and inter-temporal feedback types. Each feedback type is evaluated based on criteria such as frequency, consistency, informativeness, and cognitive burden.

Description

Supervisor

Korpi-Lagg, Maarit

Thesis advisor

Asadi, Mahsa

Keywords

human-in-the-loop, human feedback in reinforcement learning

Other note

Citation

Permanent link to this item

https://urn.fi/URN:NBN:fi:aalto-202502182437

Collections

[kand] Perustieteiden korkeakoulu / SCI