{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:09:53Z","timestamp":1740100193114,"version":"3.37.3"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100009011","name":"Ontario Centres of Excellence","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009011","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9533459","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T21:27:41Z","timestamp":1632173261000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic Planning Networks"],"prefix":"10.1109","author":[{"given":"Norman","family":"Tasfi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miriam","family":"Capretz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","article-title":"Adaptive computation time for recurrent neural networks","author":"graves","year":"2016","journal-title":"ArXiv Preprint"},{"year":"2017","author":"farquhar","key":"ref31"},{"key":"ref30","article-title":"Lecture 6.5-RmsProp: Divide the gradient by a running average of its recent magnitude","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Networks for Machine Learning"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref11","article-title":"Treeqn and atreec: Differentiable tree planning for deep reinforcement learning","author":"farquhar","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref12","article-title":"Imagination-augmented agents for deep reinforcement learning","author":"weber","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref13","article-title":"Strategic attentive writer for learning macroactions","author":"vezhnevets","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref14","article-title":"Learning model-based planning from scratch","author":"pascanu","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref15","article-title":"Xlvin: executed latent value iteration nets","author":"deac","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref16","article-title":"Action-conditional video prediction using deep networks in atari games","volume":"abs 1507 8750","author":"oh","year":"2015","journal-title":"CoRR"},{"key":"ref17","article-title":"Recurrent environment simulators","author":"chiappa","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/518"},{"key":"ref19","article-title":"Value prediction network","volume":"abs 1707 3497","author":"oh","year":"2017","journal-title":"CoRR"},{"key":"ref28","first-page":"2146","article-title":"Value iteration networks","author":"tamar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref27","article-title":"Combined reinforcement learning via abstract representations","author":"fran\u00e7ois-lavet","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref3","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/105971239300100403"},{"key":"ref29","article-title":"On learning to think: Algorithmic information theory for novel combinations of reinforcement learning controllers and recurrent neural world models","author":"schmidhuber","year":"2015","journal-title":"ArXiv Preprint"},{"journal-title":"Reinforcement Learning An Introduction","year":"2017","author":"sutton","key":"ref5"},{"key":"ref8","first-page":"1071","article-title":"Learning neural network policies with guided policy search under unknown dynamics","author":"levine","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref7","first-page":"465","article-title":"Pileo: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"0","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"key":"ref2","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-75538-8_7"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref20","first-page":"3769","article-title":"Monte-Carlo tree search as regularized policy optimization","volume":"119","author":"grill","year":"0","journal-title":"Proceedings of the 37th International Conference on Machine Learning ser Proceedings of Machine Learning Research"},{"key":"ref22","first-page":"1281","article-title":"Intrinsically motivated reinforcement learning","author":"chentanez","year":"2005","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref24","first-page":"2829","article-title":"Continuous deep q-learning with model-based acceleration","author":"gu","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref26","article-title":"The predictron: End-to-end learning and planning","author":"silver","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref25","article-title":"Learning to search with mctsnets","author":"guez","year":"2018","journal-title":"ArXiv Preprint"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2021,7,18]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09533459.pdf?arnumber=9533459","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:45:52Z","timestamp":1652197552000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9533459\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9533459","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}