{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T11:15:05Z","timestamp":1787915705041,"version":"build-2784847793"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T00:00:00Z","timestamp":1666742400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T00:00:00Z","timestamp":1666742400000},"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":[[2022,10,26]]},"DOI":"10.1109\/uemcon54665.2022.9965711","type":"proceedings-article","created":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T20:55:15Z","timestamp":1669928115000},"page":"0052-0058","source":"Crossref","is-referenced-by-count":15,"title":["Meta Reinforcement Learning with Hebbian Learning"],"prefix":"10.1109","author":[{"given":"Di","family":"Wang","sequence":"first","affiliation":[{"name":"University of Illinois at Chicago,Department of Mechanical and Industrial Engineering,Chicago,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09816-7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3377930.3390214"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.013"},{"key":"ref30","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013779"},{"key":"ref35","article-title":"Like what you like: Knowledge distill via neuron selectivity transfer","author":"huang","year":"2017"},{"key":"ref34","article-title":"Distilling the knowledge in a neural network","volume":"2","author":"hinton","year":"2015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.08.003"},{"key":"ref11","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref12","first-page":"1531","article-title":"A natural policy gradient","author":"kakade","year":"2002","journal-title":"Advances in neural information processing systems"},{"key":"ref13","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref14","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref15","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3117790"},{"key":"ref17","first-page":"5279","article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","author":"wu","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref19","article-title":"Distributed distributional deterministic policy gradients","author":"barth-maron","year":"2018"},{"key":"ref28","author":"haykin","year":"2010","journal-title":"Neural Networks and Learning Machines 3\/E"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-011-5235-x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2018-85683"},{"key":"ref6","article-title":"Richard E Turner, and Sergey Levine. Q-prop: Sample-efficient policy gradient with an off-policy critic","author":"gu","year":"2016"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2007.4424781"},{"key":"ref5","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"ICLRE"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/app10165631"},{"key":"ref7","article-title":"Meta reinforcement learning with latent variable gaussian processes","author":"s\u00e6mundsson","year":"2018"},{"key":"ref2","article-title":"Some considerations on learning to explore via meta-reinforcement learning","author":"stadie","year":"2018"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.06.015"},{"key":"ref9","author":"schmitt","year":"2018","journal-title":"Deep reinforcement learning"},{"key":"ref20","first-page":"7780","article-title":"Offline meta-reinforcement learning with advantage weighting","author":"mitchell","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref22","first-page":"25747","article-title":"Robust task representations for offline meta-reinforcement learning via contrastive learning","author":"yuan","year":"2022","journal-title":"International Conference on Machine Learning"},{"key":"ref21","article-title":"Meta-reinforcement learning of structured exploration strategies","volume":"31","author":"gupta","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref24","first-page":"20719","article-title":"Meta-learning through hebbian plasticity in random networks","volume":"33","author":"najarro","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"Meta-gradient reinforcement learning","volume":"31","author":"xu","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_32"},{"key":"ref25","article-title":"Data-efficient hierarchical reinforcement learning","volume":"31","author":"nachum","year":"2018","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2022 IEEE 13th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","location":"New York, NY, NY, USA","start":{"date-parts":[[2022,10,26]]},"end":{"date-parts":[[2022,10,29]]}},"container-title":["2022 IEEE 13th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9965569\/9965624\/09965711.pdf?arnumber=9965711","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:09:27Z","timestamp":1671480567000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9965711\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,26]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/uemcon54665.2022.9965711","relation":{},"subject":[],"published":{"date-parts":[[2022,10,26]]}}}