Cooperative Bayesian Optimization for Imperfect Agents

arXiv:2403.04442v1 Announce Type: new
Abstract: We introduce a cooperative Bayesian optimization problem for optimizing black-box functions of two variables where two agents choose together at which points to query the function but have only control over one variable each. This setting is inspired by human-AI teamwork, where an AI-assistant helps its human user solve a problem, in this simplest case, collaborative optimization. We formulate the solution as sequential decision-making, where the agent we control models the user as a computationally …

abstract agents arxiv assistant bayesian box control cs.ai cs.lg cs.ma function functions human optimization query solve teamwork together type variables