{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:47:51Z","timestamp":1730270871042,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","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-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-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10342281","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T14:17:55Z","timestamp":1702477075000},"page":"7348-7353","source":"Crossref","is-referenced-by-count":1,"title":["Asynchronous, Option-Based Multi-Agent Policy Gradient: A Conditional Reasoning Approach"],"prefix":"10.1109","author":[{"given":"Xubo","family":"Lyu","sequence":"first","affiliation":[{"name":"School of Computing Science, Simon Fraser University,BC,Canada"}]},{"given":"Amin","family":"Banitalebi-Dehkordi","sequence":"additional","affiliation":[{"name":"Huawei Technologies Canada Co., Ltd.,Burnaby,BC,Canada"}]},{"given":"Mo","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computing Science, Simon Fraser University,BC,Canada"}]},{"given":"Yong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Technologies Canada Co., Ltd.,Burnaby,BC,Canada"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"journal-title":"Revisiting some common practices in cooperative multi-agent reinforcement learning","year":"2022","author":"Fu","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/545056.545078"},{"key":"ref4","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Rashid","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"journal-title":"The surprising effectiveness of ppo in cooperative, multi-agent games","year":"2021","author":"Yu","key":"ref6"},{"key":"ref7","first-page":"1223","article-title":"Anomaly detection in multi-agent trajectories for automated driving","volume-title":"Conference on Robot Learning","author":"Wiederer","year":"2022"},{"key":"ref8","first-page":"1132","article-title":"Influencing towards stable multi-agent interactions","volume-title":"Conference on robot learning","author":"Wang","year":"2022"},{"issue":"06906","key":"ref9","volume":"2003","author":"Wang","year":"2020","journal-title":"Model-based reinforcement learning for decentralized multiagent rendezvous"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/375735.376302"},{"key":"ref11","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume":"29","author":"Kulkarni","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref13","article-title":"Meta learning shared hierarchies","volume-title":"International Conference on Learning Representations","author":"Frans","year":"2018"},{"journal-title":"Hierarchical robot navigation in novel environments using rough 2-d maps","year":"2021","author":"Xu","key":"ref14"},{"key":"ref15","first-page":"1566","article-title":"Hierarchical cooperative multiagent reinforcement learning with skill discovery","volume-title":"Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems","author":"Yang","year":"2020"},{"key":"ref16","first-page":"2306","article-title":"Multi-level structure vs. end-to-end-learning in high-performance tactile robotic manipulation","volume-title":"Conference on Robot Learning","author":"Voigt","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1177\/105971230501300301"},{"volume-title":"Asynchronous multi-agent actor-critic with macro-actions","year":"2022","author":"Xiao","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-29911-8_7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11418"},{"key":"ref21","first-page":"1146","article-title":"Macro-action-based deep multi-agent reinforcement learning","volume-title":"Conference on Robot Learning","author":"Xiao","year":"2020"},{"journal-title":"Playing atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref22"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref25","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning","author":"Schulman","year":"2015"},{"journal-title":"Ai2-thor: An interactive 3d environment for visual ai","year":"2017","author":"Kolve","key":"ref26"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2023,10,1]]},"location":"Detroit, MI, USA","end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10342281.pdf?arnumber=10342281","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T20:27:51Z","timestamp":1705004871000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342281\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342281","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}