{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T13:02:12Z","timestamp":1765976532342,"version":"3.37.3"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T00:00:00Z","timestamp":1629158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T00:00:00Z","timestamp":1629158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T00:00:00Z","timestamp":1629158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100009148","name":"QMUL","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009148","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,8,17]]},"DOI":"10.1109\/cog52621.2021.9619093","type":"proceedings-article","created":{"date-parts":[[2021,12,7]],"date-time":"2021-12-07T20:53:06Z","timestamp":1638910386000},"page":"1-8","source":"Crossref","is-referenced-by-count":4,"title":["Generalising Discrete Action Spaces with Conditional Action Trees"],"prefix":"10.1109","author":[{"given":"Christopher","family":"Bamford","sequence":"first","affiliation":[]},{"given":"Alvaro","family":"Ovalle","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Griddly A platform for ai research in games","year":"2020","author":"bamford","key":"ref10"},{"key":"ref11","first-page":"2754","article-title":"Autore-gressive policies for continuous control deep reinforcement learning","author":"korenkevych","year":"2019","journal-title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence"},{"journal-title":"Deep reinforcement learning for automated stock trading an ensemble strategy","year":"2020","author":"yang","key":"ref12"},{"key":"ref13","article-title":"A closer look at invalid action masking in policy gradient algorithms","author":"huang","year":"2020","journal-title":"ArXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8848063"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grandmaster level in StarCraft II using multi-agent reinforcement learning","volume":"575","author":"vinyals","year":"2019","journal-title":"Nature"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/316"},{"key":"ref17","article-title":"Comparing observation and action representations for deep reinforcement learning in µrts","author":"huang","year":"2019","journal-title":"ArXiv"},{"journal-title":"Measuring generalization of deep reinforcement learning applied to real-time strategy games","year":"0","author":"huang","key":"ref18"},{"key":"ref19","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures","author":"espeholt","year":"2018","journal-title":"ArXiv"},{"key":"ref4","article-title":"The StarCraft multi-agent challenge","author":"samvelyan","year":"2019","journal-title":"ArXiv"},{"key":"ref3","article-title":"StarCraft II: A new challenge for reinforcement learning","author":"vinyals","year":"2017","journal-title":"ArXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2017.2738156"},{"key":"ref5","first-page":"58","article-title":"The combinatorial multi-armed bandit problem and its application to real-time strategy games","author":"onta\u00f1\u00f3n","year":"0","journal-title":"Proceedings of the Ninth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment ser AIIDE'13"},{"key":"ref8","article-title":"Combinatorial optimization by graph pointer networks and hierarchical reinforcement learning","author":"ma","year":"2019","journal-title":"ArXiv"},{"journal-title":"Dota 2 with large scale deep reinforcement learning","year":"2019","author":"berner","key":"ref7"},{"key":"ref2","first-page":"1934","article-title":"Reinforcement learning with parameterized actions","author":"masson","year":"0","journal-title":"Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence ser AAAI'16"},{"key":"ref1","article-title":"Action space shaping in deep reinforcement learning","author":"kanervisto","year":"2020","journal-title":"ArXiv"},{"journal-title":"Graph constrained reinforcement learning for natural language action spaces","year":"2020","author":"ammanabrolu","key":"ref9"},{"key":"ref20","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref22","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"ziebart","year":"2008","journal-title":"AAAI"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490403"},{"key":"ref23","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","author":"haarnoja","year":"0","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2021 IEEE Conference on Games (CoG)","start":{"date-parts":[[2021,8,17]]},"location":"Copenhagen, Denmark","end":{"date-parts":[[2021,8,20]]}},"container-title":["2021 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9618888\/9618891\/09619093.pdf?arnumber=9619093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:53:34Z","timestamp":1652201614000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9619093\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,17]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/cog52621.2021.9619093","relation":{},"subject":[],"published":{"date-parts":[[2021,8,17]]}}}