{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T07:42:51Z","timestamp":1723016571590},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7]]},"abstract":"Researchers have shown that neural networks are vulnerable to adversarial examples and subtle environment changes. The resulting errors can look like blunders to humans, eroding trust in these agents. In prior games research, agent evaluation often focused on the in-practice game outcomes. Such evaluation typically fails to evaluate robustness to worst-case outcomes. Computer poker research has examined how to assess such worst-case performance. Unfortunately, exact computation is infeasible with larger domains, and existing approximations are poker-specific. We introduce ISMCTS-BR, a scalable search-based deep reinforcement learning algorithm for learning a best response to an agent, approximating worst-case performance. We demonstrate the technique in several games against a variety of agents, including several AlphaZero-based agents. Supplementary material is available at https:\/\/arxiv.org\/abs\/2004.09677.<\/jats:p>","DOI":"10.24963\/ijcai.2022\/484","type":"proceedings-article","created":{"date-parts":[[2022,7,16]],"date-time":"2022-07-16T02:55:56Z","timestamp":1657940156000},"page":"3487-3493","source":"Crossref","is-referenced-by-count":1,"title":["Approximate Exploitability: Learning a Best Response"],"prefix":"10.24963","author":[{"given":"Finbarr","family":"Timbers","sequence":"first","affiliation":[{"name":"DeepMind"}]},{"given":"Nolan","family":"Bard","sequence":"additional","affiliation":[{"name":"DeepMind"}]},{"given":"Edward","family":"Lockhart","sequence":"additional","affiliation":[{"name":"DeepMind"}]},{"given":"Marc","family":"Lanctot","sequence":"additional","affiliation":[{"name":"Deepmind"}]},{"given":"Martin","family":"Schmid","sequence":"additional","affiliation":[{"name":"DeepMind"}]},{"given":"Neil","family":"Burch","sequence":"additional","affiliation":[{"name":"University of Alberta"},{"name":"DeepMind"}]},{"given":"Julian","family":"Schrittwieser","sequence":"additional","affiliation":[{"name":"DeepMind"}]},{"given":"Thomas","family":"Hubert","sequence":"additional","affiliation":[{"name":"DeepMind"}]},{"given":"Michael","family":"Bowling","sequence":"additional","affiliation":[{"name":"DeepMind"},{"name":"University of Alberta"}]}],"member":"10584","event":{"number":"31","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2022","name":"Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}","start":{"date-parts":[[2022,7,23]]},"theme":"Artificial Intelligence","location":"Vienna, Austria","end":{"date-parts":[[2022,7,29]]}},"container-title":["Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T11:09:57Z","timestamp":1658142597000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2022\/484"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":0,"URL":"http:\/\/dx.doi.org\/10.24963\/ijcai.2022\/484","relation":{},"subject":[],"published":{"date-parts":[[2022,7]]}}}
