Batch Prioritization in Multigoal Reinforcement Learning
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Vecchietti, Luiz Felipe | - |
dc.contributor.author | Kim, Taeyoung | - |
dc.contributor.author | Choi, Kyujin | - |
dc.contributor.author | Hong, Junhee | - |
dc.contributor.author | Har, Dongsoo | - |
dc.date.available | 2020-08-24T01:35:16Z | - |
dc.date.created | 2020-08-24 | - |
dc.date.issued | 2020-07 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/78031 | - |
dc.description.abstract | In multigoal reinforcement learning, an agent interacts with an environment and learns to achieve multiple goals. The goal-conditioned policy is trained to effectively generalize its behavior for multiple goals. During training, the experiences collected by the agent are randomly sampled from a replay buffer. Because biased sampling of achieved goals affects the success rate of a given task, it should be avoided by considering the valid goal space, introduced here as the set of goals to achieve, and the current competence of the policy. To this end, a novel prioritization method for creation of batches, e.g., collections of samples, is proposed. Candidate batches are sampled and associated with costs; in each iteration the batch with the minimum cost is chosen to train the policy. The cost function is modeled by an intended goal, which is proposed as a hypothetical goal that the policy is trying to learn in each cycle, and the information of the valid goal space. The minimum cost of the batch selected for each iteration decreases throughout training as the policy learns to achieve goals near the center of the valid goal space. The proposed batch prioritization method is combined with hindsight experience replay (HER) for experiments in robotic control tasks presented in the OpenAI gym suite to demonstrate learning performance comparable to that of other state-of-the-art prioritization methods. As a result, the proposed batch prioritization method can achieve improved learning performance in 4 out of 5 tasks, particularly for harder tasks. The experimental results suggest that the proposed method for the creation of training batches, using the valid goal space information and current competence of the policy, can enhance learning performance in multigoal tasks with high-dimensional goal space. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.relation.isPartOf | IEEE ACCESS | - |
dc.title | Batch Prioritization in Multigoal Reinforcement Learning | - |
dc.type | Article | - |
dc.type.rims | ART | - |
dc.description.journalClass | 1 | - |
dc.identifier.wosid | 000557774300001 | - |
dc.identifier.doi | 10.1109/ACCESS.2020.3012204 | - |
dc.identifier.bibliographicCitation | IEEE ACCESS, v.8, pp.137449 - 137461 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.scopusid | 2-s2.0-85090113302 | - |
dc.citation.endPage | 137461 | - |
dc.citation.startPage | 137449 | - |
dc.citation.title | IEEE ACCESS | - |
dc.citation.volume | 8 | - |
dc.contributor.affiliatedAuthor | Hong, Junhee | - |
dc.type.docType | Article | - |
dc.subject.keywordAuthor | Training | - |
dc.subject.keywordAuthor | Task analysis | - |
dc.subject.keywordAuthor | Learning (artificial intelligence) | - |
dc.subject.keywordAuthor | Robots | - |
dc.subject.keywordAuthor | Erbium | - |
dc.subject.keywordAuthor | Cost function | - |
dc.subject.keywordAuthor | Aerospace electronics | - |
dc.subject.keywordAuthor | Experience replay | - |
dc.subject.keywordAuthor | batch prioritization | - |
dc.subject.keywordAuthor | goal distribution | - |
dc.subject.keywordAuthor | reinforcement learning | - |
dc.subject.keywordAuthor | intended goal | - |
dc.subject.keywordPlus | LEVEL | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Telecommunications | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Telecommunications | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
1342, Seongnam-daero, Sujeong-gu, Seongnam-si, Gyeonggi-do, Republic of Korea(13120)031-750-5114
COPYRIGHT 2020 Gachon University All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.