{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T20:47:08Z","timestamp":1767991628362,"version":"3.49.0"},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1109\/cig.2018.8490398","type":"proceedings-article","created":{"date-parts":[[2018,10,16]],"date-time":"2018-10-16T03:37:41Z","timestamp":1539661061000},"page":"1-8","source":"Crossref","is-referenced-by-count":31,"title":["Imitation Learning with Concurrent Actions in 3D Games"],"prefix":"10.1109","author":[{"given":"Jack","family":"Harmer","sequence":"first","affiliation":[]},{"given":"Linus","family":"Gisslen","sequence":"additional","affiliation":[]},{"given":"Jorge","family":"del Val","sequence":"additional","affiliation":[]},{"given":"Henrik","family":"Holst","sequence":"additional","affiliation":[]},{"given":"Joakim","family":"Bergdahl","sequence":"additional","affiliation":[]},{"given":"Tom","family":"Olsson","sequence":"additional","affiliation":[]},{"given":"Kristoffer","family":"Sjoo","sequence":"additional","affiliation":[]},{"given":"Magnus","family":"Nordin","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","author":"kim","year":"2013","journal-title":"Approximate policy iteration with demonstration data"},{"key":"ref11","article-title":"Hierarchical Imitation and Reinforcement Learning","author":"le","year":"2018","journal-title":"CoRR"},{"key":"ref12","article-title":"Continuous Control With Deep Reinforcement Learning","author":"lillicrap","year":"2015","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref14","author":"mnih","year":"2016","journal-title":"Asynchronous methods for deep reinforcement learning"},{"key":"ref15","article-title":"Overcoming Exploration in Reinforcement Learning with Demonstrations","author":"nair","year":"2017","journal-title":"CoRR"},{"key":"ref16","article-title":"Policy invariance under reward transformations : Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"Sixteenth International Conference on Machine Learning"},{"key":"ref17","author":"ross","year":"2010","journal-title":"A reduction of imitation learning and structured prediction to no-regret online learning"},{"key":"ref18","author":"schaal","year":"1997","journal-title":"Learning from demonstration"},{"key":"ref19","first-page":"1","article-title":"Prioritized Experience Replay","author":"schaul","year":"2015","journal-title":"CoRR"},{"key":"ref28","article-title":"Pretraining Deep Actor-Critic Reinforcement Learning Algorithms With Expert Demonstrations","author":"zhang","year":"2018","journal-title":"CoRR"},{"key":"ref4","article-title":"Noisy Networks for Exploration","author":"fortunato","year":"2017","journal-title":"CoRR"},{"key":"ref27","article-title":"Dueling Network Architectures for Deep Reinforcement Learning","author":"wang","year":"2016"},{"key":"ref3","article-title":"A Distributional Perspective on Reinforcement Learning","author":"bellemare","year":"2017","journal-title":"CoRR"},{"key":"ref6","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref5","article-title":"Reinforcement Learning from Imperfect Demonstrations","author":"gao","year":"2018","journal-title":"CoRR"},{"key":"ref8","article-title":"Deep Q-learning from Demonstrations","author":"hester","year":"2017","journal-title":"CoRR"},{"key":"ref7","author":"haarnoja","year":"2018","journal-title":"Soft actor-critic Off-policy maximum entropy deep reinforcement learning with a stochastic actor"},{"key":"ref2","author":"babaeizadeh","year":"2016","journal-title":"GA3C GPU-based A3C for Deep Reinforcement Learning"},{"key":"ref9","article-title":"Learning from Demonstrations for Real World Reinforcement Learning","author":"hester","year":"2017","journal-title":"CoRR"},{"key":"ref1","article-title":"Learning High-level Representations from Demonstrations","author":"andersen","year":"2018","journal-title":"CoRR"},{"key":"ref20","article-title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","author":"schulman","year":"2015","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref21","article-title":"Learning to Factor Policies and Action-Value Functions: Factored Action Space Representations for Deep Reinforcement learning","author":"sharma","year":"2017","journal-title":"CoRR"},{"key":"ref24","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref23","article-title":"Exploration from Demonstration for Interactive Reinforcement Learning","author":"subramanian","year":"2016","journal-title":"AAMAS"},{"key":"ref26","author":"wang","year":"2016","journal-title":"Exploring Multi-Action Relationship in Reinforcement Learning"},{"key":"ref25","article-title":"Deep Reinforcement Learning with Double Q-learning","author":"van hasselt","year":"2015","journal-title":"CoRR"}],"event":{"name":"2018 IEEE Conference on Computational Intelligence and Games (CIG)","location":"Maastricht","start":{"date-parts":[[2018,8,14]]},"end":{"date-parts":[[2018,8,17]]}},"container-title":["2018 IEEE Conference on Computational Intelligence and Games (CIG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8473398\/8490359\/08490398.pdf?arnumber=8490398","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T22:05:04Z","timestamp":1643234704000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8490398\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/cig.2018.8490398","relation":{},"subject":[],"published":{"date-parts":[[2018,8]]}}}