{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T04:12:05Z","timestamp":1772770325785,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9636234","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T20:45:38Z","timestamp":1639687538000},"page":"5627-5634","source":"Crossref","is-referenced-by-count":8,"title":["PNS: Population-Guided Novelty Search for Reinforcement Learning in Hard Exploration Environments"],"prefix":"10.1109","author":[{"given":"Qihao","family":"Liu","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Laboratory for Computational Sensing and Robotics,Baltimore,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujia","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","first-page":"1223","article-title":"More effective distributed ml via a stale synchronous parallel parameter server","author":"ho","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2739480.2754664"},{"key":"ref32","first-page":"4644","article-title":"On learning intrinsic rewards for policy gradient methods","author":"zheng","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"Openai gym","author":"brockman","year":"2016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322259"},{"key":"ref36","first-page":"19","article-title":"Communication efficient distributed machine learning with the parameter server","author":"li","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref35","first-page":"1223","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref34","article-title":"Cem-rl: Combining evolutionary and gradient-based methods for policy search","author":"pourchot","year":"2018"},{"key":"ref10","first-page":"1109","article-title":"Vime: Variational information maximizing exploration","author":"houthooft","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref12","article-title":"Population based training of neural networks","author":"jaderberg","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"key":"ref14","article-title":"Population-guided parallel policy search for reinforcement learning","author":"jung","year":"2020"},{"key":"ref15","article-title":"Massively parallel methods for deep reinforcement learning","author":"nair","year":"2015"},{"key":"ref16","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref17","article-title":"Reinforcement learning through asynchronous advantage actor-critic on a gpu","author":"babaeizadeh","year":"2016"},{"key":"ref18","article-title":"Accelerated methods for deep reinforcement learning","author":"stooke","year":"2018"},{"key":"ref19","article-title":"Distributed prioritized experience replay","author":"horgan","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2908812.2908929"},{"key":"ref4","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2013.6557731"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref6","first-page":"4344","article-title":"Learning by playing solving sparse reward tasks from scratch","author":"riedmiller","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref29","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018"},{"key":"ref5","article-title":"Curiosity-driven experience prioritization via density estimation","author":"zhao","year":"2019"},{"key":"ref8","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202244"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794102"},{"key":"ref9","first-page":"8388","article-title":"Learning to play with intrinsically-motivated, self-aware agents","author":"haber","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref1","first-page":"4026","article-title":"Deep exploration via bootstrapped dqn","author":"osband","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","author":"espeholt","year":"2018"},{"key":"ref22","first-page":"2","article-title":"Alphastar: Mastering the real-time strategy game starcraft ii","author":"vinyals","year":"2019","journal-title":"DeepMind blog"},{"key":"ref21","article-title":"Impact: Importance weighted asynchronous architectures with clipped target networks","author":"luo","year":"2019"},{"key":"ref24","first-page":"5027","article-title":"Improving exploration in evolution strategies for deep reinforcement learning via a population of novelty-seeking agents","author":"conti","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3319619.3321894"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1569901.1569918"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2001576.2001606"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Prague, Czech Republic","start":{"date-parts":[[2021,9,27]]},"end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9635848\/9635849\/09636234.pdf?arnumber=9636234","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T23:53:56Z","timestamp":1670284436000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9636234\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9636234","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}