ReLExS: Reinforcement Learning Explanations for Stackelberg No-Regret Learners
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916369672437760 |
|---|---|
| author | Huang, Xiangge Li, Jingyuan Xie, Jiaqing |
| author_facet | Huang, Xiangge Li, Jingyuan Xie, Jiaqing |
| contents | With the constraint of a no regret follower, will the players in a two-player Stackelberg game still reach Stackelberg equilibrium? We first show when the follower strategy is either reward-average or transform-reward-average, the two players can always get the Stackelberg Equilibrium. Then, we extend that the players can achieve the Stackelberg equilibrium in the two-player game under the no regret constraint. Also, we show a strict upper bound of the follower's utility difference between with and without no regret constraint. Moreover, in constant-sum two-player Stackelberg games with non-regret action sequences, we ensure the total optimal utility of the game remains also bounded. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_14086 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ReLExS: Reinforcement Learning Explanations for Stackelberg No-Regret Learners Huang, Xiangge Li, Jingyuan Xie, Jiaqing Computer Science and Game Theory Machine Learning With the constraint of a no regret follower, will the players in a two-player Stackelberg game still reach Stackelberg equilibrium? We first show when the follower strategy is either reward-average or transform-reward-average, the two players can always get the Stackelberg Equilibrium. Then, we extend that the players can achieve the Stackelberg equilibrium in the two-player game under the no regret constraint. Also, we show a strict upper bound of the follower's utility difference between with and without no regret constraint. Moreover, in constant-sum two-player Stackelberg games with non-regret action sequences, we ensure the total optimal utility of the game remains also bounded. |
| title | ReLExS: Reinforcement Learning Explanations for Stackelberg No-Regret Learners |
| topic | Computer Science and Game Theory Machine Learning |
| url | https://arxiv.org/abs/2408.14086 |