Criticality-Based Advice in Reinforcement Learning (Student Abstract)

Yitzhak Spielberg, Amos Azaria

פרסום מחקרי: פרק בספר / בדוח / בכנספרסום בספר כנסביקורת עמיתים

תקציר

One of the ways to make reinforcement learning (RL) more efficient is by utilizing human advice. Since human advice is expensive, the central question in advice-based reinforcement learning is, how to decide in which states the agent should ask for advice. To approach this challenge, various advice strategies have been proposed. Although all of these strategies distribute advice more efficiently than naive strategies, they rely solely on the agent's estimate of the action-value function, and therefore, are rather inefficient when this estimate is not accurate, in particular, in the early stages of the learning process. To address this weakness, we present an approach to advice-based RL, in which the human's role is not limited to giving advice in chosen states, but also includes hinting a-priori, before the learning procedure, in which sub-domains of the state space the agent might require more advice. For this purpose we use the concept of critical: states in which choosing the proper action is more important than in other states.

שפה מקוריתאנגלית
כותר פרסום המארחIAAI-22, EAAI-22, AAAI-22 Special Programs and Special Track, Student Papers and Demonstrations
מוציא לאורAssociation for the Advancement of Artificial Intelligence
עמודים13057-13058
מספר עמודים2
מסת"ב (אלקטרוני)1577358767, 9781577358763
מזהי עצם דיגיטלי (DOIs)
סטטוס פרסוםפורסם - 30 יוני 2022
אירוע36th AAAI Conference on Artificial Intelligence, AAAI 2022 - Virtual, Online
משך הזמן: 22 פבר׳ 20221 מרץ 2022

סדרות פרסומים

שםProceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022
כרך36

כנס

כנס36th AAAI Conference on Artificial Intelligence, AAAI 2022
עירVirtual, Online
תקופה22/02/221/03/22

טביעת אצבע

להלן מוצגים תחומי המחקר של הפרסום 'Criticality-Based Advice in Reinforcement Learning (Student Abstract)'. יחד הם יוצרים טביעת אצבע ייחודית.

פורמט ציטוט ביבליוגרפי