Agent Tamer The Secret Life Of Algorithms

Simple item page
dc.contributor.authorIrene Olayinka
dc.contributor.authorCalarina Muslimani
dc.contributor.authorMatthew Taylor
dc.date.accessioned2025-05-01T22:15:20Z
dc.date.available2025-05-01T22:15:20Z
dc.date.issued2021-08-01
dc.descriptionAlthough this report deals with the mechanisms of artificially intelligent rather than intelligence agents, the former is no less a subject of fascination. My research centred around an algorithm called Training an Agent Manually via Evaluative Reinforcement (TAMER), which incorporates human feedback into a reinforcement learning model. I ran several trials in the Mountain Car environment provided by the OpenAI gym library, altering the uniform value, credit assignment value, and budget of each to see which changes returned the best performance for the agent. Ultimately, lower credit assignment values and uniform values that are slightly better than those an average human trainer can provide are most effective in improving the performance of the agent, while the budget does not have a significant effect on the agent's efficiency.
dc.identifier.doihttps://doi.org/10.7939/r3-n78h-g120
dc.language.isoen
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/
dc.subjectWISEST
dc.subjectSTEM
dc.subjectSRP
dc.subjectScience
dc.subjectComputing Science
dc.subjectartificial intelligence
dc.subjectTraining an Agent Manually via Evaluative Reinforcement
dc.subjectTAMER
dc.titleAgent Tamer The Secret Life Of Algorithms
dc.typehttp://purl.org/coar/resource_type/c_6670
ual.jupiterAccesshttp://terms.library.ualberta.ca/public

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
Olayinka_Irene_Agent _Tamer_The_Secret_Life_of_Algorithms_SRP_2021.pdf
Size:
1.2 MB
Format:
Adobe Portable Document Format
Download

Collections

WISEST Research Posters