Inverse Game Theory for Stackelberg Games: The Blessing of Bounded Rationality
391
13
Microsoft Research334 тыс
Следующее
12.12.22 – 73230:03Популярные
205 дней – 10 04426:38
Опубликовано 12 декабря 2022, 20:34
2022 Data-driven Optimization Workshop: Inverse Game Theory for Stackelberg Games: the Blessing of Bounded Rationality
Speaker: Weiran Shen, Renmin University of China
Optimizing strategic decisions (a.k.a. computing equilibrium) is key to the success of many non-cooperative multi-agent applications. However, in many real-world situations, we may face the exact opposite of this game-theoretic problem — instead of prescribing equilibrium of a given game, we may directly observe the agents’ equilibrium behaviors but want to infer the underlying parameters of an unknown game. This research question, also known as inverse game theory, has been studied in multiple recent works in the context of Stackelberg games. Unfortunately, existing works exhibit quite negative results, showing statistical hardness and computational hardness, assuming follower’s perfectly rational behaviors. Our work relaxes the perfect rationality agent assumption to the classic quantal response model, a more realistic behavior model of bounded rationality. Interestingly, we show that the smooth property brought by such bounded rationality model actually leads to provably more efficient learning of the follower utility parameters in general Stackelberg games. Systematic empirical experiments on synthesized games confirm our theoretical results and further suggest its robustness beyond the strict quantal response model.
Speaker: Weiran Shen, Renmin University of China
Optimizing strategic decisions (a.k.a. computing equilibrium) is key to the success of many non-cooperative multi-agent applications. However, in many real-world situations, we may face the exact opposite of this game-theoretic problem — instead of prescribing equilibrium of a given game, we may directly observe the agents’ equilibrium behaviors but want to infer the underlying parameters of an unknown game. This research question, also known as inverse game theory, has been studied in multiple recent works in the context of Stackelberg games. Unfortunately, existing works exhibit quite negative results, showing statistical hardness and computational hardness, assuming follower’s perfectly rational behaviors. Our work relaxes the perfect rationality agent assumption to the classic quantal response model, a more realistic behavior model of bounded rationality. Interestingly, we show that the smooth property brought by such bounded rationality model actually leads to provably more efficient learning of the follower utility parameters in general Stackelberg games. Systematic empirical experiments on synthesized games confirm our theoretical results and further suggest its robustness beyond the strict quantal response model.
Свежие видео
16 дней – 18 8750:16
23 дня – 8011:33
23 дня – 4721:24
23 дня – 12934:25
32 дня – 11 6630:52Случайные видео
1 день – 147 7911:00
9 дней – 2 5410:49
23.03.23 – 99815:51
13.12.22 – 1 1695:57
10.12.22 – 2172:21
3 дня – 5480:49
3 дня – 1 069 20933:33
3 дня – 20 05816:32
6 дней – 6270:32
8 дней – 253 96616:28
9 дней – 159 1870:16
9 дней – 44711:06
3 дня – 6510:17
