{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:51:42Z","timestamp":1772905902083,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10651449","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["A Method of Path Planning and Intelligent Exploration for Robot Based on Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Xianglin","family":"Lyu","sequence":"first","affiliation":[{"name":"China Three Gorges University,Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering,Yichang,China"}]},{"given":"Zhaoxiang","family":"Zang","sequence":"additional","affiliation":[{"name":"China Three Gorges University,Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering,Yichang,China"}]},{"given":"Sibo","family":"Li","sequence":"additional","affiliation":[{"name":"China Three Gorges University,Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering,Yichang,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11132035"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11132084"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-022-04348-z"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2972862"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-019-01106-x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3010461"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.10.020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/sym13061061"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1049\/itr2.12067"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.03.105"},{"issue":"3","key":"ref14","first-page":"755","article-title":"Multi-agent decision-making method based on Actor-Critic framework and its application in wargame","volume":"43","author":"Li","year":"2021","journal-title":"Systems Engineering and Electronics"},{"key":"ref15","first-page":"1407","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Espeholt"},{"key":"ref16","first-page":"1312","article-title":"Prioritized Experience Replay","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Schaul"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4340"},{"key":"ref18","first-page":"3878","article-title":"Self-imitation learning","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Oh"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636140"},{"key":"ref20","first-page":"1","article-title":"Deep Recurrent Q-Learning for Partially Observable mdps","volume-title":"Proceedings of the 2015 Association for the Advancement of Artificial Intelligence Fall Symposium Series","author":"Hausknecht"},{"key":"ref21","first-page":"93","article-title":"How can we define intrinsic motivation","volume-title":"Proceedings of eighth International Conference on Epi-genetic Robotics: Modeling Cognitive Development in Robotic Systems","author":"Oudeyer"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref23","first-page":"1","article-title":"Exploration by random network distillation","volume-title":"Proceeding of the 7th International Conference on Learning Representations","author":"Burda"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2018.03.104"},{"key":"ref25","first-page":"1889","article-title":"Trust Region Policy Optimization","author":"Schulman","year":"2015","journal-title":"Computer Science"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8121558"},{"issue":"4","key":"ref27","first-page":"3008","volume":"11","author":"Haarnoja","year":"2018","journal-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor"},{"issue":"11","key":"ref28","first-page":"4217","article-title":"A review of deep reinforcement learning methods based on sample efficiency optimization","volume":"33","author":"Junwei","year":"2022","journal-title":"Journal of Software"},{"issue":"02","key":"ref29","first-page":"119","article-title":"Robot local path planning based on improved PPO algorithm","volume":"49","author":"Liu","year":"2023","journal-title":"Computer Engineering"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref31","volume-title":"Minimalistic grid world environment for openai gym [EB\/OL]","author":"Chevalier-BoisvertM Willems","year":"2018"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10651449.pdf?arnumber=10651449","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T06:33:41Z","timestamp":1725950021000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10651449\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10651449","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}