Conference proceeding
Contextual Combinatorial Bandits in Real-Time Strategy Games
2021 IEEE Conference on Games (CoG), pp 1-9
17 Aug 2021
Abstract
The contextual bandit problem is a richer framework than stochastic bandits that has many applications since it allows the learner has access to additional information (the "context"). This additional information can help predict the expected utility of the different arms in many cases. Moreover, combinatorial bandits are a class of bandit problem where the space of possible arms to choose from has a combinatorial structure. In this paper, we investigate the bandit problem where we have both contextual information and there is a combinatorial arm structure, which we call contextual combinatorial bandits (CCMABs). We apply contextual combinatorial bandits to realtime strategy (RTS) games, and study different algorithms to solve CCMABs with different trade-offs of computational efficiency and learning biases. Specifically, we focus on the problem of determining map-specific game playing policies, and formulate it as a CCMABs.
Metrics
17 Record Views
1 citations in Scopus
Details
- Title
- Contextual Combinatorial Bandits in Real-Time Strategy Games
- Creators
- Zuozhi Yang - Drexel UniversitySantiago Ontanon - Drexel University
- Publication Details
- 2021 IEEE Conference on Games (CoG), pp 1-9
- Conference
- 2021 IEEE Conference on Games (CoG)
- Publisher
- IEEE
- Number of pages
- 1
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Computer Science
- Scopus ID
- 2-s2.0-85122919486
- Other Identifier
- 991019174898604721