{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T06:08:21Z","timestamp":1749794901903,"version":"3.37.3"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/iv55152.2023.10186792","type":"proceedings-article","created":{"date-parts":[[2023,7,27]],"date-time":"2023-07-27T17:20:05Z","timestamp":1690478405000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Multi-agent Decision-making at Unsignalized Intersections with Reinforcement Learning from Demonstrations"],"prefix":"10.1109","author":[{"given":"Chang","family":"Huang","sequence":"first","affiliation":[{"name":"Tongji University,Department of Computer Science and Technology,China"}]},{"given":"Junqiao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tongji University,Department of Computer Science and Technology,China"}]},{"given":"Hongtu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tongji University,Department of Computer Science and Technology,China"}]},{"given":"Hai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tongji University,Department of Computer Science and Technology,China"}]},{"given":"Xiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tongji University,Department of Computer Science and Technology,China"}]},{"given":"Chen","family":"Ye","sequence":"additional","affiliation":[{"name":"Tongji University,Department of Computer Science and Technology,China"}]}],"member":"263","reference":[{"journal-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","year":"2017","author":"vecerik","key":"ref13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref15","first-page":"2052","article-title":"Off-Policy Deep Reinforcement Learning without Exploration","author":"fujimoto","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2022-Fall57202.2022.10012835"},{"key":"ref11","first-page":"178:7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"rashid","year":"2022","journal-title":"The Journal of Machine Learning Research"},{"key":"ref10","first-page":"3040","article-title":"Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning","author":"jaques","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3200747"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995969"},{"key":"ref17","article-title":"Time-to-collision and collision avoidance systems","author":"van der horst","year":"1994","journal-title":"Verkeersgedrag in Onderzoek"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref16"},{"key":"ref19","first-page":"3757","article-title":"Episodic Multi-agent Reinforcement Learning with Curiosity-driven Exploration","volume":"34","author":"zheng","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","volume":"30","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"journal-title":"An Environment for Autonomous Driving Decision-Making","year":"2018","author":"leurent","key":"ref24"},{"journal-title":"Exploiting semantic epsilon greedy exploration strategy in multi-agent reinforcement learning","year":"2022","author":"tse","key":"ref23"},{"journal-title":"The surprising effectiveness of mappo in cooperative multi -agent games","year":"2021","author":"yu","key":"ref26"},{"journal-title":"EMERGENT COMPLEXITY VIA MULTI-AGENT COMPETITION","year":"2017","author":"bansal","key":"ref25"},{"key":"ref20","article-title":"Learning from Demonstration","volume":"9","author":"schaal","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827073"},{"journal-title":"Rethinking the implementation tricks and monotonicity constraint in cooperative multi-agent reinforcement learning","year":"2021","author":"hu","key":"ref27"},{"key":"ref8","article-title":"MAVEN: Multi-Agent Variational Exploration","volume":"32","author":"mahajan","year":"2019","journal-title":"Advances in neural information processing systems"},{"journal-title":"Exploration in deep reinforcement learning A comprehensive survey","year":"2021","author":"yang","key":"ref7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2022.3196925"},{"key":"ref4","first-page":"10 784","article-title":"Learning to Simulate Self-driven Particles System with Coordinated Policy Optimization","volume":"34","author":"peng","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564720"},{"key":"ref6","first-page":"1","article-title":"Coordination for Connected and Automated Vehicles At Non-Signalized Intersections: A Value Decomposition-Based Multiagent Deep Reinforcement Learning Approach","author":"guo","year":"2022","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"ref5","first-page":"1","article-title":"Cooperative Multiagent Deep Deterministic Policy Gradient (CoMADDPG) for Intelligent Connected Transportation with Unsignalized Intersection","volume":"2020","author":"wu","year":"2020","journal-title":"Mathematical Problems in Engineering"}],"event":{"name":"2023 IEEE Intelligent Vehicles Symposium (IV)","start":{"date-parts":[[2023,6,4]]},"location":"Anchorage, AK, USA","end":{"date-parts":[[2023,6,7]]}},"container-title":["2023 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10186382\/10186383\/10186792.pdf?arnumber=10186792","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T17:36:06Z","timestamp":1692034566000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10186792\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/iv55152.2023.10186792","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}