{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T07:50:22Z","timestamp":1725695422815},"reference-count":37,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,6]]},"DOI":"10.1109\/ivs.2018.8500712","type":"proceedings-article","created":{"date-parts":[[2018,10,23]],"date-time":"2018-10-23T00:56:23Z","timestamp":1540256183000},"source":"Crossref","is-referenced-by-count":34,"title":["Decentralized Cooperative Planning for Automated Vehicles with Hierarchical Monte Carlo Tree Search"],"prefix":"10.1109","author":[{"given":"Karl","family":"Kurzer","sequence":"first","affiliation":[]},{"given":"Chenyang","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"J.","family":"Marius Zollner","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"Local path planning and motion control for agv in positioning","author":"takahashi","year":"1989","journal-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2015.349"},{"key":"ref31","article-title":"Decentralized control of partially observable markov decision pro- cesses using belief space macro-actions","author":"omidshafiei","year":"2015","journal-title":"International Conference on Robotics and Automation"},{"key":"ref30","article-title":"Planning with Macro-Actions in Decentralized POMDPs","author":"amato","year":"2014","journal-title":"International Conference on Autonomous Agents and Multi-Agent Systems"},{"key":"ref37","article-title":"Monte-Carlo Planning in Large POMDPs","author":"silver","year":"2010","journal-title":"Advances in Neural Information Processing Systems NIPS"},{"key":"ref36","article-title":"Comparing uct versus cfr in simul- taneous games","author":"schaeffer","year":"2009"},{"key":"ref35","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"International Conference on Machine Learning ICML"},{"key":"ref34","article-title":"An Algorithm for Distributed Reinforce- ment Learning in Cooperative Multi-Agent Systems","author":"lauer","year":"2000","journal-title":"International Conference on Machine Learning ICML"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1126\/science.7466396","article-title":"The Evolution of Cooperation","author":"axelrod","year":"1981","journal-title":"Science"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/INISTA.2014.6873612"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/9.486636"},{"key":"ref13","article-title":"Cooperative cognitive automo- biles","author":"stiller","year":"2007","journal-title":"IEEE Intelligent Vehicles Symposium"},{"key":"ref14","article-title":"Advanced cooperative decentralized deci- sion making using a cooperative reward system","author":"pascheka","year":"2015","journal-title":"IEEE International Symposium on Innovations in Intelligent Systems and Applications"},{"key":"ref15","article-title":"Tactical cooperative planning for au- tonomous highway driving using Monte-Carlo Tree Search","author":"lenz","year":"2016","journal-title":"IEEE Intelligent Vehicles Symposium"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2200894"},{"key":"ref17","article-title":"Tactical Planning Using MCTS in the Game of Star- Craft","author":"soemers","year":"2014"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref19","article-title":"Intra-option learning about temporally abstract actions","author":"sutton","year":"1998","journal-title":"ICML"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-006-7035-4"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref27","article-title":"Hierarchical Approaches to Concurrency, Multiagency, and Partial Observability","author":"mahadevan","year":"2004","journal-title":"Learning and Approximate Dynamic Programming Scaling up to the Real World"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1613\/jair.5507","article-title":"On Monte Carlo Tree Search and Re- inforcement Learning Spyridon Samothrakis","author":"vodopivec","year":"2017","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"ref29","doi-asserted-by":"crossref","article-title":"Learning for Multi-robot Cooperation in Partially Observable Stochastic Environments with Macro-actions","author":"liu","year":"2017","DOI":"10.1109\/IROS.2017.8206001"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1038\/nature24270","article-title":"Mastering the game of Go without human knowledge","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref8","article-title":"Recent advances in hierarchical reinforcement learning","author":"barto","year":"2003","journal-title":"Discrete Event Dynamic Systems"},{"key":"ref7","article-title":"A sparse sampling algorithm for near-optimal planning in large Markov decision processes","author":"kearns","year":"1999","journal-title":"IJCAI Int Joint Conf on Artificial Intelligence"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2013.06.016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2014.6932889"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2015.2508009"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2013.2263884"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2012.6374161"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206505"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860383"},{"key":"ref26","article-title":"Markovian state and action abstractions for MDPs via hierarchical MCTS","author":"bai","year":"2016","journal-title":"IJCAI Int Joint Conf on Artificial Intelligence"},{"key":"ref25","article-title":"Hierarchical Monte-Carlo Planning","author":"toussaint","year":"2015","journal-title":"AAAI Confer- ence on Artificial Intelligence"}],"event":{"name":"2018 IEEE Intelligent Vehicles Symposium (IV)","location":"Changshu","start":{"date-parts":[[2018,6,26]]},"end":{"date-parts":[[2018,6,30]]}},"container-title":["2018 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8472796\/8500355\/08500712.pdf?arnumber=8500712","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T19:38:32Z","timestamp":1643225912000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8500712\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/ivs.2018.8500712","relation":{},"subject":[],"published":{"date-parts":[[2018,6]]}}}
