{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T09:17:51Z","timestamp":1730279871540,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/iwcia47330.2019.8955073","type":"proceedings-article","created":{"date-parts":[[2020,1,15]],"date-time":"2020-01-15T02:40:24Z","timestamp":1579056024000},"page":"47-52","source":"Crossref","is-referenced-by-count":0,"title":["Diversifying experiences in multi agent reinforcement learning"],"prefix":"10.1109","author":[{"given":"N.A.V","family":"Suryanarayanan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iba","family":"Hitoshi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1007\/978-3-319-64816-3_5","article-title":"A Neuroevolutionary Approach to Adaptive Multi-agent Teams","author":"bryant","year":"2018","journal-title":"Foundations of Trusted Autonomy"},{"journal-title":"Evolution-Guided Policy Gradient in Reinforcement Learning","year":"2018","author":"khadka","key":"ref11"},{"journal-title":"CEM-RL Combining evolutionary and gradient-based methods for policy search","year":"2018","author":"pourchot","key":"ref12"},{"journal-title":"Evolution strategies as a scalable alternative to reinforcement learning","year":"2017","author":"salimans","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"journal-title":"Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents","year":"2017","author":"conti","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_29"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"journal-title":"Soft actor-critic Off-policy maximum entropy deep reinforcement learning with a stochastic actor","year":"2018","author":"haarnoja","key":"ref18"},{"journal-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref19"},{"key":"ref4","first-page":"41","volume":"33","author":"tuyls","year":"2012","journal-title":"Multiagent Learning Basics Challenges and Prospects"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2016.06.011"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref5","first-page":"4190","article-title":"A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning","author":"lanctot","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-07418-3_9"},{"key":"ref7","first-page":"2829","article-title":"Continuous Deep Q-Learning with Model-based Acceleration","author":"gu","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-005-2631-2"},{"journal-title":"A deeper look at experience replay","year":"2017","author":"zhang","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/106365602320169811"},{"journal-title":"Hindsight Experience Replay","year":"2017","author":"andrychowicz","key":"ref20"},{"journal-title":"OpenAI Gym","year":"2016","author":"greg","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1111\/j.0030-1299.2005.13735.x"},{"journal-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","year":"2017","author":"lowe","key":"ref24"},{"key":"ref23","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2019 IEEE 11th International Workshop on Computational Intelligence and Applications (IWCIA)","start":{"date-parts":[[2019,11,9]]},"location":"Hiroshima, Japan","end":{"date-parts":[[2019,11,10]]}},"container-title":["2019 IEEE 11th International Workshop on Computational Intelligence and Applications (IWCIA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8949434\/8955001\/08955073.pdf?arnumber=8955073","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T20:18:57Z","timestamp":1658261937000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8955073\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/iwcia47330.2019.8955073","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}