{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:24:31Z","timestamp":1730298271476,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,23]],"date-time":"2024-06-23T00:00:00Z","timestamp":1719100800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,23]],"date-time":"2024-06-23T00:00:00Z","timestamp":1719100800000},"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":[[2024,6,23]]},"DOI":"10.1109\/sose62659.2024.10620974","type":"proceedings-article","created":{"date-parts":[[2024,8,9]],"date-time":"2024-08-09T17:18:50Z","timestamp":1723223930000},"page":"140-146","source":"Crossref","is-referenced-by-count":0,"title":["Fear based Intrinsic Reward as a Barrier Function for Continuous Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Rodney","family":"Sanchez","sequence":"first","affiliation":[{"name":"Rochester Institute of Technology,Dept of Electrical and Microelectronic Engineering,Rochester,USA"}]},{"given":"Ferat","family":"Sahin","sequence":"additional","affiliation":[{"name":"Rochester Institute of Technology,Dept of Electrical and Microelectronic Engineering,Rochester,USA"}]},{"given":"Jamison","family":"Heard","sequence":"additional","affiliation":[{"name":"Rochester Institute of Technology,Dept of Electrical and Microelectronic Engineering,Rochester,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"article-title":"Continuous control with deep reinforcement learning","volume-title":"4th International Conference on Learning Representations, ICLR 2016 - Conference Track Proceedings","author":"Lillicrap","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3216996"},{"key":"ref4","article-title":"THE ROLE OF PRETRAINED REPRESENTATIONS FOR THE OOD GENERALIZATION OF RL AGENTS","volume-title":"ICLR","author":"Tr\u00e4uble","year":"2022"},{"article-title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","year":"2020","author":"Srinivas","key":"ref5"},{"volume-title":"Reinforcement Learning: An Introduction Second edition, in progress","year":"2018","author":"Sutton","key":"ref6"},{"key":"ref7","article-title":"Deep reinforcement learning with experience replay based on SARSA","volume-title":"SSCI","author":"Zhao","year":"2018"},{"key":"ref8","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"ICML","author":"Ng","year":"1999"},{"key":"ref9","article-title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","volume":"36","author":"Chevalier-Boisvert","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.10.902"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109241"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21236\/ADA440280"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/e25020327"},{"key":"ref14","article-title":"HIERARCHICAL REINFORCEMENT LEARNING BY DISCOVERING INTRINSIC OPTIONS","volume-title":"ICLR","author":"Zhang","year":"2021"},{"volume-title":"LEARNING SUBGOAL REPRESENTATIONS WITH SLOW DYNAMICS","author":"Li","key":"ref15"},{"key":"ref16","article-title":"Exploration by Random Network Distillation","volume-title":"ICLR","author":"Burda","year":"2019"},{"article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","year":"2018","author":"Haarnoja","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpr.2008.05.003"},{"issue":"1","key":"ref19","article-title":"Vicarious conditioned fear acquisition and extinction in child\u2013parent dyads","volume-title":"Scientific Reports","volume":"10","author":"Marin","year":"2020"},{"issue":"1","key":"ref20","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1007\/BF03393102","article-title":"Understanding Observational Learning: An Interbehavioral Approach","volume":"27","author":"Fryling","year":"2011","journal-title":"The Analysis of Verbal Behavior"},{"key":"ref21","article-title":"Meta-Learning with Memory-Augmented Neural Networks Google DeepMind","volume":"abs\/1605.06065","author":"Santoro","year":"2016"},{"article-title":"Neural Turing Machines","year":"2014","author":"Graves","key":"ref22"},{"article-title":"Correlation Matrix Memories: Improving Performance for Capacity and Generalisation","year":"2011","author":"Hobson","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"}],"event":{"name":"2024 19th Annual System of Systems Engineering Conference (SoSE)","start":{"date-parts":[[2024,6,23]]},"location":"Tacoma, WA, USA","end":{"date-parts":[[2024,6,26]]}},"container-title":["2024 19th Annual System of Systems Engineering Conference (SoSE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10620912\/10620920\/10620974.pdf?arnumber=10620974","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T04:02:04Z","timestamp":1723435324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10620974\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,23]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/sose62659.2024.10620974","relation":{},"subject":[],"published":{"date-parts":[[2024,6,23]]}}}