File Download

There are no files associated with this item.

  • Find it @ UNIST can give you direct access to the published full text of this article. (UNISTARs only)
Related Researcher

한승열

Han, Seungyul
Machine Learning & Intelligent Control Lab.
Read More

Views & Downloads

Detailed Information

Cited time in webofscience Cited time in scopus
Metadata Downloads

Full metadata record

DC Field Value Language
dc.citation.conferencePlace US -
dc.citation.conferencePlace Virtual -
dc.citation.title International Conference on Machine Learning -
dc.contributor.author Han, Seungyul -
dc.contributor.author Sung, Youngchul -
dc.date.accessioned 2024-01-31T21:38:20Z -
dc.date.available 2024-01-31T21:38:20Z -
dc.date.created 2021-11-28 -
dc.date.issued 2021-07-20 -
dc.description.abstract In this paper, sample-aware policy entropy regularization is proposed to enhance the conventional policy entropy regularization for better exploration. Exploiting the sample distribution obtainable from the replay buffer, the proposed sample-aware entropy regularization maximizes the entropy of the weighted sum of the policy action distribution and the sample action distribution from the replay buffer for sample-efficient exploration. A practical algorithm named diversity actor-critic (DAC) is developed by applying policy iteration to the objective function with the proposed sample-aware entropy regularization. Numerical results show that DAC significantly outperforms existing recent algorithms for reinforcement learning. -
dc.identifier.bibliographicCitation International Conference on Machine Learning -
dc.identifier.scopusid 2-s2.0-85129829387 -
dc.identifier.uri https://scholarworks.unist.ac.kr/handle/201301/77155 -
dc.identifier.url https://icml.cc/virtual/2021/spotlight/10270 -
dc.publisher International Conference on Machine Learning -
dc.title Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration -
dc.type Conference Paper -
dc.date.conferenceDate 2021-07-18 -

qrcode

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.