{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T06:20:55Z","timestamp":1768803655417,"version":"3.49.0"},"reference-count":78,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"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":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892771","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-10","source":"Crossref","is-referenced-by-count":4,"title":["Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Control"],"prefix":"10.1109","author":[{"given":"Takuya","family":"Kanazawa","sequence":"first","affiliation":[{"name":"Hitachi America, Ltd. R&D,Industrial AI Lab,Santa Clara,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiyan","family":"Wang","sequence":"additional","affiliation":[{"name":"Hitachi America, Ltd. R&D,Industrial AI Lab,Santa Clara,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chetan","family":"Gupta","sequence":"additional","affiliation":[{"name":"Hitachi America, Ltd. R&D,Industrial AI Lab,Santa Clara,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2018.2823641"},{"key":"ref72","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"4th International Conference on Learning Representations ICLR 2016"},{"key":"ref71","article-title":"Randomized prior functions for deep reinforcement learning","author":"osband","year":"2018","journal-title":"Proceedings of the 32Nd International Conference on Neural Information Processing Systems"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.omega.2014.12.006"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.segan.2020.100413"},{"key":"ref77","author":"fan","year":"2021","journal-title":"PowerGym A reinforcement learning environment for Volt-Var control in power distribution systems"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/PVSC.2018.8547862"},{"key":"ref39","article-title":"Worst cases policy gradients","author":"tang","year":"2019","journal-title":"3rd Annual Conference on Robot Learning CoRL 2019"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2020.03.001"},{"key":"ref38","article-title":"Adaptively calibrated critic estimates for deep reinforcement learning","volume":"abs 2111 12673","author":"dorka","year":"2021","journal-title":"CoRR"},{"key":"ref78","article-title":"Soft actor-critic with integer actions","volume":"abs 2109 8512","author":"fan","year":"2021","journal-title":"CoRR"},{"key":"ref33","article-title":"SENTINEL: taming uncertainty with ensemble-based distributional reinforcement learning","volume":"abs 2102 11075","author":"eriksson","year":"2021","journal-title":"CoRR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/476"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793505"},{"key":"ref30","article-title":"Distributional advantage actor-critic","volume":"abs 1806 6914","author":"li","year":"2018","journal-title":"CoRR"},{"key":"ref37","article-title":"Sample-based distributional policy gradient","volume":"abs 2001 2652","author":"singh","year":"2020","journal-title":"CoRR"},{"key":"ref36","author":"chen","year":"2017","journal-title":"Ucb exploration via q-ensembles"},{"key":"ref35","article-title":"Deep exploration via bootstrapped DQN","author":"osband","year":"2016","journal-title":"Annual Conference on Neural Information Processing Systems 2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref60","article-title":"A survey of exploration methods in reinforcement learning","volume":"abs 2109 157","author":"amin","year":"2021","journal-title":"CoRR"},{"key":"ref62","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","author":"lakshminarayanan","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS 2017)"},{"key":"ref61","article-title":"Exploration in deep reinforcement learning: A comprehensive survey","volume":"abs 2109 6668","author":"yang","year":"2021","journal-title":"CoRR"},{"key":"ref63","author":"li","year":"2021","journal-title":"Neural network ensembles Theory training and the importance of explicit diversity"},{"key":"ref28","article-title":"Controlling overestimation bias with truncated mixture of continuous distributional quantile critics","author":"kuznetsov","year":"2020","journal-title":"Proceedings of the 37th International Conference on Machine Learning ICML 2020"},{"key":"ref64","author":"pearce","year":"2018","journal-title":"Bayesian inference with anchored ensembles of neural networks and application to exploration in reinforcement learning"},{"key":"ref27","author":"ma","year":"2020","journal-title":"DSAC Distributional Soft Actor Critic for risk-sensitive reinforcement learning"},{"key":"ref65","article-title":"Uncertainty in Neural Networks: Approximately Bayesian Ensembling","author":"pearce","year":"0","journal-title":"The 23rd International Conference on Artificial Intelligence and Statistics AISTATS 2020"},{"key":"ref66","author":"hoffmann","year":"2021","journal-title":"Deep ensembles from a Bayesian perspective"},{"key":"ref29","article-title":"GMAC: A distributional perspective on actor-critic framework","author":"nam","year":"2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning ICML 2021"},{"key":"ref67","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning ICML 2018"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1126\/science.153.3731.34"},{"key":"ref69","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"2nd International Conference on Learning Representations ICLR 2014"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","first-page":"13:1","article-title":"Learning the variance of the reward-to-go","volume":"17","author":"tamar","year":"0","journal-title":"J Mach Learn Res"},{"key":"ref22","article-title":"Parametric return density estimation for reinforcement learning","author":"morimura","year":"2010","journal-title":"Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence (UAI 2010)"},{"key":"ref21","article-title":"Bayesian Q-learning","author":"dearden","year":"0","journal-title":"Proceedings of the Fifteenth National Conference on Artificial Intelligence and Tenth Innovative Applications of Artificial Intelligence Conference AAAI 98 IAAI 98"},{"key":"ref24","article-title":"Statistics and samples in distributional reinforcement learning","author":"rowland","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning ICML 2019"},{"key":"ref23","article-title":"Nonparametric return distribution approximation for reinforcement learning","author":"morimura","year":"2010","journal-title":"Proceedings of the 27th International Conference on Machine Learning (ICML-10)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref25","article-title":"Fully parameterized quantile function for distributional reinforcement learning","author":"yang","year":"2019","journal-title":"Annual Conference on Neural Information Processing Systems 2019 NeurIPS 2019"},{"key":"ref50","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning ICML 2018"},{"key":"ref51","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc\u00eda","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref59","article-title":"Algorithms for CVaR optimization in MDPs","author":"chow","year":"2014","journal-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21314\/JOR.2000.038"},{"key":"ref57","author":"jorion","year":"2006","journal-title":"Value at Risk The New Benchmark for Managing Financial Risk"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1086\/294846"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/BF00122574"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017940631555"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17302"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-97628-0_17"},{"key":"ref10","article-title":"ADER: adapting between exploration and robustness for actor-critic methods","volume":"abs 2109 3443","author":"zhou","year":"2021","journal-title":"CoRR"},{"key":"ref11","article-title":"A distributional perspective on reinforcement learning","volume":"abs 1707 6887","author":"bellemare","year":"2017","journal-title":"CoRR"},{"key":"ref40","article-title":"Improving robustness via risk averse distributional reinforcement learning","author":"singh","year":"2020","journal-title":"Proceedings of the 2nd Annual Conference on Learning for Dynamics and Control L4DC 2020"},{"key":"ref12","article-title":"Implicit quantile networks for distributional reinforcement learning","author":"dabney","year":"0","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref13","article-title":"Estimating risk and uncertainty in deep reinforcement learning","volume":"abs 1905 9638","author":"clements","year":"2019","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5870"},{"key":"ref15","article-title":"Distributed distributional deterministic policy gradients","volume":"abs 1804 8617","author":"barth-maron","year":"2018","journal-title":"CoRR"},{"key":"ref16","article-title":"Better exploration with optimistic actor critic","author":"ciosek","year":"2019","journal-title":"Annual Conference on Neural Information Processing Systems 2019 NeurIPS 2019"},{"key":"ref17","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"4th International Conference on Learning Representations ICLR 2016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1017\/S0021900200023123"},{"key":"ref19","article-title":"Temporal difference methods for the variance of the reward to go","author":"tamar","year":"2013","journal-title":"Proceedings of the 30th International Conference on Machine Learning ICML 2013"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.strusafe.2008.06.020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05946-3"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.05.008"},{"key":"ref8","article-title":"Distributional reinforcement learning for efficient exploration","author":"mavrin","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning ICML 2019"},{"key":"ref7","article-title":"Distributional reinforcement learning with quantile regression","volume":"abs 1710 10044","author":"dabney","year":"2017","journal-title":"CoRR"},{"key":"ref49","article-title":"Double Q-learning","author":"van hasselt","year":"2010","journal-title":"24th Annual Conference on Neural Information Processing Systems 2010"},{"key":"ref9","article-title":"Information-directed exploration for deep reinforcement learning","author":"nikolov","year":"2019","journal-title":"7th International Conference on Learning Representations ICLR 2019"},{"key":"ref46","article-title":"Uncertainty-driven imagination for continuous deep reinforcement learning","author":"kalweit","year":"2017","journal-title":"CoRL 2017-1st Annual Conf Robot Learn"},{"key":"ref45","article-title":"Continuous control with ensemble deep deterministic policy gradients","volume":"abs 2111 15382","author":"januszewski","year":"2021","journal-title":"CoRR"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015789"},{"key":"ref47","article-title":"Learning to run with actor-critic ensemble","volume":"abs 1712 8987","author":"huang","year":"2017","journal-title":"CoRR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560962"},{"key":"ref41","article-title":"Risk-averse offline reinforcement learning","author":"urp\u00ed","year":"2021","journal-title":"9th International Conference on Learning Representations ICLR 2021"},{"key":"ref44","article-title":"SUNRISE: A simple unified framework for ensemble learning in deep reinforcement learning","author":"lee","year":"2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning ICML 2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/444"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","location":"Padua, Italy","start":{"date-parts":[[2022,7,18]]},"end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892771.pdf?arnumber=9892771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:26:55Z","timestamp":1667525215000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892771","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}