{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T20:55:00Z","timestamp":1782334500691,"version":"3.54.5"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1016\/j.neunet.2023.08.025","type":"journal-article","created":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T21:18:39Z","timestamp":1692652719000},"page":"104-117","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":8,"special_numbering":"C","title":["Cross-domain policy adaptation with dynamics alignment"],"prefix":"10.1016","volume":"167","author":[{"given":"Haiyuan","family":"Gui","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5705-1218","authenticated-orcid":false,"given":"Shanchen","family":"Pang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shihang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sibo","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9990-5912","authenticated-orcid":false,"given":"Yufeng","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2925-2362","authenticated-orcid":false,"given":"Xue","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2023.08.025_b1","series-title":"Twenty-ninth AAAI conference on artificial intelligence","article-title":"Unsupervised cross-domain transfer in policy gradient reinforcement learning via manifold alignment","author":"Ammar","year":"2015"},{"key":"10.1016\/j.neunet.2023.08.025_b2","series-title":"Proceedings of the 11th international conference on autonomous agents and multiagent systems, Vol. 1","first-page":"383","article-title":"Reinforcement learning transfer via sparse coding","author":"Ammar","year":"2012"},{"key":"10.1016\/j.neunet.2023.08.025_b3","series-title":"International conference on machine learning","first-page":"176","article-title":"Averaged-dqn: Variance reduction and stabilization for deep reinforcement learning","author":"Anschel","year":"2017"},{"key":"10.1016\/j.neunet.2023.08.025_b4","series-title":"IJCAI","first-page":"672","article-title":"General game learning using knowledge transfer","author":"Banerjee","year":"2007"},{"key":"10.1016\/j.neunet.2023.08.025_b5","article-title":"Successor features for transfer in reinforcement learning","volume":"30","author":"Barreto","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2023.08.025_b6","article-title":"Boltzmann exploration done right","volume":"30","author":"Cesa-Bianchi","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2023.08.025_b7","series-title":"Evolving reinforcement learning algorithms","author":"Co-Reyes","year":"2021"},{"key":"10.1016\/j.neunet.2023.08.025_b8","series-title":"International conference on machine learning","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"},{"issue":"11","key":"10.1016\/j.neunet.2023.08.025_b9","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Communications of the ACM"},{"key":"10.1016\/j.neunet.2023.08.025_b10","series-title":"International conference on machine learning","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","author":"Haarnoja","year":"2017"},{"key":"10.1016\/j.neunet.2023.08.025_b11","series-title":"International conference on machine learning","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"10.1016\/j.neunet.2023.08.025_b12","article-title":"Double Q-learning","volume":"23","author":"Hasselt","year":"2010","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2023.08.025_b13","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"12627","article-title":"Sim-to-real via sim-to-sim: Data-efficient robotic grasping via randomized-to-canonical adaptation networks","author":"James","year":"2019"},{"key":"10.1016\/j.neunet.2023.08.025_b14","series-title":"Conference on robot learning","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","author":"Jang","year":"2022"},{"issue":"2","key":"10.1016\/j.neunet.2023.08.025_b15","doi-asserted-by":"crossref","first-page":"4630","DOI":"10.1109\/LRA.2022.3151396","article-title":"Concurrent training of a control policy and a state estimator for dynamic and robust legged locomotion","volume":"7","author":"Ji","year":"2022","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.neunet.2023.08.025_b16","series-title":"2018 IEEE international conference on robotics and automation","first-page":"7525","article-title":"Cross-domain transfer in reinforcement learning using target apprentice","author":"Joshi","year":"2018"},{"key":"10.1016\/j.neunet.2023.08.025_b17","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.neunet.2020.12.023","article-title":"T-soft update of target network for deep reinforcement learning","volume":"136","author":"Kobayashi","year":"2021","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2023.08.025_b18","series-title":"NeurIPS ML safety workshop","article-title":"Spectral robustness analysis of deep imitation learning","author":"Korkmaz","year":"2022"},{"key":"10.1016\/j.neunet.2023.08.025_b19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neunet.2022.12.018","article-title":"STACoRe: Spatio-temporal and action-based contrastive representations for reinforcement learning in Atari","volume":"160","author":"Lee","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2023.08.025_b20","series-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015"},{"key":"10.1016\/j.neunet.2023.08.025_b21","series-title":"2018 IEEE international conference on robotics and automation","first-page":"1118","article-title":"Imitation from observation: Learning to imitate behaviors from raw video via context translation","author":"Liu","year":"2018"},{"key":"10.1016\/j.neunet.2023.08.025_b22","series-title":"The eleventh international conference on learning representations","article-title":"Benchmarking constraint inference in inverse reinforcement learning","author":"Liu","year":"2023"},{"key":"10.1016\/j.neunet.2023.08.025_b23","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"7655","article-title":"Efficient continuous control with double actors and regularized critics","author":"Lyu","year":"2022"},{"issue":"3","key":"10.1016\/j.neunet.2023.08.025_b24","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1023\/B:AIRE.0000036264.95672.64","article-title":"Transfer of experience between reinforcement learning environments with progressive difficulty","volume":"21","author":"Madden","year":"2004","journal-title":"Artificial Intelligence Review"},{"key":"10.1016\/j.neunet.2023.08.025_b25","series-title":"International conference on machine learning","first-page":"3692","article-title":"Smoothed action value functions for learning gaussian policies","author":"Nachum","year":"2018"},{"key":"10.1016\/j.neunet.2023.08.025_b26","series-title":"Icml, Vol. 99","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"Ng","year":"1999"},{"key":"10.1016\/j.neunet.2023.08.025_b27","series-title":"Icml, Vol. 1","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","author":"Ng","year":"2000"},{"key":"10.1016\/j.neunet.2023.08.025_b28","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.neunet.2022.11.008","article-title":"Bayesian Disturbance Injection: Robust imitation learning of flexible policies for robot manipulation","volume":"158","author":"Oh","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2023.08.025_b29","first-page":"11767","article-title":"Softmax deep double deterministic policy gradients","volume":"33","author":"Pan","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2023.08.025_b30","series-title":"Reinforcement learning with dynamic boltzmann softmax updates","author":"Pan","year":"2019"},{"key":"10.1016\/j.neunet.2023.08.025_b31","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume":"1","author":"Pomerleau","year":"1988","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"10.1016\/j.neunet.2023.08.025_b32","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1162\/neco.1991.3.1.88","article-title":"Efficient training of artificial neural networks for autonomous navigation","volume":"3","author":"Pomerleau","year":"1991","journal-title":"Neural Computation"},{"key":"10.1016\/j.neunet.2023.08.025_b33","series-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"Ross","year":"2011"},{"key":"10.1016\/j.neunet.2023.08.025_b34","series-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"10.1016\/j.neunet.2023.08.025_b35","series-title":"Imitation from arbitrary experience: A dual unification of reinforcement and imitation learning methods","author":"Sikchi","year":"2023"},{"key":"10.1016\/j.neunet.2023.08.025_b36","series-title":"Avid: Learning multi-stage tasks via pixel-level translation of human videos","author":"Smith","year":"2019"},{"key":"10.1016\/j.neunet.2023.08.025_b37","series-title":"International conference on machine learning","first-page":"5916","article-title":"Revisiting the softmax bellman operator: New benefits and new perspective","author":"Song","year":"2019"},{"key":"10.1016\/j.neunet.2023.08.025_b38","article-title":"Multi-agent generative adversarial imitation learning","volume":"31","author":"Song","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2023.08.025_b39","series-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"10.1016\/j.neunet.2023.08.025_b40","series-title":"Proceedings of the 24th international conference on machine learning","first-page":"879","article-title":"Cross-domain transfer for reinforcement learning","author":"Taylor","year":"2007"},{"issue":"7","key":"10.1016\/j.neunet.2023.08.025_b41","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"Taylor","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2023.08.025_b42","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2023.02.025","article-title":"Deep learning-based open set multi-source domain adaptation with complementary transferability metric for mechanical fault diagnosis","author":"Tian","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2023.08.025_b43","series-title":"2012 IEEE\/RSJ international conference on intelligent robots and systems","first-page":"5026","article-title":"Mujoco: A physics engine for model-based control","author":"Todorov","year":"2012"},{"issue":"4","key":"10.1016\/j.neunet.2023.08.025_b44","doi-asserted-by":"crossref","first-page":"10922","DOI":"10.1109\/LRA.2022.3196139","article-title":"Model-based imitation learning using entropy regularization of model and policy","volume":"7","author":"Uchibe","year":"2022","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.neunet.2023.08.025_b45","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1016\/j.neunet.2021.08.017","article-title":"Forward and inverse reinforcement learning sharing network weights and hyperparameters","volume":"144","author":"Uchibe","year":"2021","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2023.08.025_b46","series-title":"Proceedings of the AAAI conference on artificial intelligence, Vol. 30","article-title":"Deep reinforcement learning with double q-learning","author":"Van\u00a0Hasselt","year":"2016"},{"key":"10.1016\/j.neunet.2023.08.025_b47","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2022.124657","article-title":"Strategic bidding in a competitive electricity market: An intelligent method using Multi-Agent Transfer Learning based on reinforcement learning","volume":"256","author":"Wu","year":"2022","journal-title":"Energy"},{"key":"10.1016\/j.neunet.2023.08.025_b48","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1016\/j.neunet.2023.01.025","article-title":"Achieving efficient interpretability of reinforcement learning via policy distillation and selective input gradient regularization","volume":"161","author":"Xing","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2023.08.025_b49","doi-asserted-by":"crossref","DOI":"10.1016\/j.ymssp.2022.109789","article-title":"TDMSAE: A transferable decoupling multi-scale autoencoder for mechanical fault diagnosis","volume":"185","author":"Yu","year":"2023","journal-title":"Mechanical Systems and Signal Processing"},{"key":"10.1016\/j.neunet.2023.08.025_b50","series-title":"The eleventh international conference on learning representations","article-title":"CLARE: Conservative model-based reward learning for offline inverse reinforcement learning","author":"Yue","year":"2023"},{"key":"10.1016\/j.neunet.2023.08.025_b51","series-title":"International conference on learning representations","article-title":"Learning cross-domain correspondence for control with dynamics cycle-consistency","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neunet.2023.08.025_b52","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"2223","article-title":"Unpaired image-to-image translation using cycle-consistent adversarial networks","author":"Zhu","year":"2017"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608023004446?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608023004446?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T02:20:18Z","timestamp":1760235618000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608023004446"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":52,"alternative-id":["S0893608023004446"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2023.08.025","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2023,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Cross-domain policy adaptation with dynamics alignment","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2023.08.025","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}]}}