Dependency Structure Search Bayesian Optimization for Decision Making Models
This addresses the scalability problem of Bayesian optimization for multi-agent systems, which is incremental but important for domains like cooperative AI.
The paper tackles the challenge of optimizing complex multi-agent decision-making models in high-dimensional settings with sparse or uninformative feedback, proposing a compact multi-layered architecture based on roles and Dependency Structure Search Bayesian Optimization to achieve improved regret bounds and strong empirical performance under malformed or sparse rewards.
Many approaches for optimizing decision making models rely on gradient based methods requiring informative feedback from the environment. However, in the case where such feedback is sparse or uninformative, such approaches may result in poor performance. Derivative-free approaches such as Bayesian Optimization mitigate the dependency on the quality of gradient feedback, but are known to scale poorly in the high-dimension setting of complex decision making models. This problem is exacerbated if the model requires interactions between several agents cooperating to accomplish a shared goal. To address the dimensionality challenge, we propose a compact multi-layered architecture modeling the dynamics of agent interactions through the concept of role. We introduce Dependency Structure Search Bayesian Optimization to efficiently optimize the multi-layered architecture parameterized by a large number of parameters, and show an improved regret bound. Our approach shows strong empirical results under malformed or sparse reward.