{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T18:12:25Z","timestamp":1774721545042,"version":"3.50.1"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"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":[[2020,10,24]]},"DOI":"10.1109\/iros45743.2020.9341777","type":"proceedings-article","created":{"date-parts":[[2021,2,13]],"date-time":"2021-02-13T02:26:48Z","timestamp":1613183208000},"page":"6098-6105","source":"Crossref","is-referenced-by-count":12,"title":["Learning Agile Locomotion via Adversarial Training"],"prefix":"10.1109","author":[{"given":"Yujin","family":"Tang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"Harada","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Addressing function approximation error in actor-critic methods","volume":"abs 1802 9477","author":"fujimoto","year":"2018","journal-title":"CoRR"},{"key":"ref38","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume":"32","author":"silver","year":"0"},{"key":"ref33","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume":"abs 1605 6676","author":"foerster","year":"2016","journal-title":"CoRR"},{"key":"ref32","first-page":"20172023","article-title":"Coordinated multi-robot exploration under communication constraints using decentralized markov decision processes","author":"matignon","year":"2012","journal-title":"Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence"},{"key":"ref31","article-title":"Multiagent bidirectionally-coordinated nets for learning to play starcraft combat games","volume":"abs 1703 10069","author":"peng","year":"2017","journal-title":"CoRR"},{"key":"ref30","first-page":"75","author":"hansen","year":"2006","journal-title":"The CMA evolution strategy A Comparing review"},{"key":"ref37","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in Neural Information Processing Systems 12"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511811654"},{"key":"ref35","article-title":"Emergence of grounded compositional language in multi-agent populations","volume":"abs 1703 4908","author":"mordatch","year":"2017","journal-title":"CoRR"},{"key":"ref34","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","author":"sukhbaatar","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref10","article-title":"Simple random search provides a competitive approach to reinforcement learning","author":"mania","year":"2018"},{"key":"ref40","article-title":"Counterfactual multi-agent policy gradients","volume":"abs 1705 8926","author":"foerster","year":"2017","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref12","first-page":"916","article-title":"Policies modulating trajectory generators","author":"iscen","year":"0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1093\/icb\/icv074"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref16","article-title":"Openai five","year":"0"},{"key":"ref17","article-title":"AlphaStar: Mastering the Real-Time Strategy Game StarCraft II","author":"vinyals","year":"2019"},{"key":"ref18","article-title":"Emergent tool use from multi-agent autocurricula","author":"baker","year":"0"},{"key":"ref19","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":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778810"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386240"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778809"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917694244"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2013.08.001"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759424"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6906945"},{"key":"ref8","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139629"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916640102"},{"key":"ref9","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914532150"},{"key":"ref46","article-title":"CMA-ES\/pycma on Github","author":"hansen","year":"2019","journal-title":"Zenodo"},{"key":"ref20","article-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","volume":"abs 1712 1815","author":"silver","year":"2017","journal-title":"CoRR"},{"key":"ref45","first-page":"2016","article-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","author":"coumans","year":"0"},{"key":"ref48","article-title":"Learning agile robotic locomotion skills by imitating animals","author":"peng","year":"2020"},{"key":"ref22","article-title":"Unsupervised pixel-level domain adaptation with generative adversarial networks","volume":"abs 1612 5424","author":"bousmalis","year":"2016","journal-title":"CoRR"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1038\/nature12295","article-title":"Locomotion dynamics of hunting in wild cheetahs","volume":"498","author":"wilson","year":"2013","journal-title":"Nature"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1006\/ijhc.1997.0162"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.2200\/S00737ED1V01Y201610AIM033"},{"key":"ref24","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume":"70","author":"pinto","year":"0"},{"key":"ref41","article-title":"Emergent complexity via multi-agent competition","volume":"abs 1710 3748","author":"bansal","year":"2017","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968306"},{"key":"ref44","article-title":"This robotics startup wants to be the boston dynamics of china","author":"guizzo","year":"2017"},{"key":"ref26","article-title":"Reducing overestimation bias in multi-agent domains using double centralized critics","author":"ackermann","year":"2019"},{"key":"ref43","first-page":"1","article-title":"Learning symmetric and low-energy locomotion","volume":"37","author":"yu","year":"2018","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref25","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"abs 1706 2275","author":"lowe","year":"2017","journal-title":"CoRR"}],"event":{"name":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Las Vegas, NV, USA","start":{"date-parts":[[2020,10,24]]},"end":{"date-parts":[[2021,1,24]]}},"container-title":["2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9340668\/9340635\/09341777.pdf?arnumber=9341777","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:56:15Z","timestamp":1656453375000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9341777\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,24]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iros45743.2020.9341777","relation":{},"subject":[],"published":{"date-parts":[[2020,10,24]]}}}