{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T21:07:04Z","timestamp":1761599224842,"version":"3.28.0"},"reference-count":28,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9533509","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T21:27:41Z","timestamp":1632173261000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Planning-integrated Policy for Efficient Reinforcement Learning in Sparse-reward Environments"],"prefix":"10.1109","author":[{"given":"Christoper","family":"Wulur","sequence":"first","affiliation":[]},{"given":"Cornelius","family":"Weber","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Wermter","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"daishi","year":"0","journal-title":"Proceedings of the Sixteenth International Conference on Machine Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2936863"},{"key":"ref12","article-title":"Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards","author":"trott","year":"2019","journal-title":"ArXiv"},{"key":"ref13","first-page":"1","article-title":"Apprenticeship learning via inverse reinforcement learning","author":"abbeel","year":"2004","journal-title":"Twenty-first international conference on Machine learning  - ICML '04"},{"key":"ref14","article-title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","author":"schrittwieser","year":"2020","journal-title":"ArXiv"},{"key":"ref15","article-title":"Dream to Control: Learning Behaviors by Latent Imagination","author":"hafner","year":"2020","journal-title":"ArXiv"},{"key":"ref16","article-title":"Learning Latent Dynamics for Planning from Pixels","author":"hafner","year":"2019","journal-title":"ArXiv"},{"key":"ref17","article-title":"Continuous Control for Searching and Planning with a Learned Model","author":"yang","year":"2020","journal-title":"ArXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.4018\/IJSIR.2016070102"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-015-7744-1"},{"journal-title":"Algorithms for inverse reinforcement learning","year":"2000","author":"ng","key":"ref28"},{"key":"ref4","article-title":"Deep Reinforcement Learning: An Overview","author":"li","year":"2018","journal-title":"ArXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"ref3","article-title":"Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning","author":"vladimir","year":"2018","journal-title":"ArXiv"},{"key":"ref6","article-title":"Imagination-Augmented Agents for Deep Reinforcement Learning","author":"weber","year":"2018","journal-title":"ArXiv"},{"key":"ref5","first-page":"8289","article-title":"Differentiable MPC for End-to-end Planning and Control","volume":"31","author":"amos","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Reinforcement learning: an introduction","author":"sutton","year":"2018","journal-title":"Adaptive Computation and Machine Learning Series"},{"key":"ref7","article-title":"Learning by Playing - Solving Sparse Reward Tasks from Scratch","author":"riedmiller","year":"2018","journal-title":"ArXiv"},{"key":"ref2","article-title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning","author":"nagabandi","year":"2017","journal-title":"ArXiv"},{"key":"ref9","article-title":"Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards","author":"vecerik","year":"2018","journal-title":"ArXiv"},{"key":"ref1","first-page":"450","article-title":"Planning with an Adaptive World Model","author":"thrun","year":"1991","journal-title":"Advances in Neural Information Processing Systems 3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2009.02.014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368199"},{"key":"ref21","first-page":"5","article-title":"Application of a radial basis function neural network for diagnosis of diabetes mellitus","volume":"91","author":"venkatesan","year":"2006","journal-title":"Current Science"},{"key":"ref24","article-title":"Model-Free Episodic Control","author":"blundell","year":"2016","journal-title":"ArXiv"},{"key":"ref23","article-title":"Addressing Function Approximation Error in Actor-Critic Methods","author":"fujimoto","year":"2018","journal-title":"ArXiv"},{"key":"ref26","article-title":"Planning to Explore via Self-Supervised World Models","author":"sekar","year":"2020","journal-title":"ArXiv"},{"key":"ref25","first-page":"9","author":"thrun","year":"1993","journal-title":"Issues in Using Function Approximation for Reinforcement Learning"}],"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\/09533509.pdf?arnumber=9533509","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:45:59Z","timestamp":1652197559000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9533509\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9533509","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}