サプライズ指数による自律意思決定システムの能力評価
Using Surprise Index for Competency Assessment in Autonomous Decision-Making
動的環境下で自律システムがタスクを遂行できるかを評価するため、観測データから予測とのずれを定量化する「サプライズ指数」を提案し、強化学習で制御される宇宙機の軌道追従問題に適用した。
著者: Akash Ratheesh, Ofer Dagan, Nisar R. Ahmed, Jay McMahon
分類: cs.RO, stat.ML
原文アブストラクト
This paper considers the problem of evaluating an autonomous system's competency in performing a task, particularly when working in dynamic and uncertain environments. The inherent opacity of machine learning models, from the perspective of the user, often described as a `black box', poses a challenge. To overcome this, we propose using a measure called the Surprise index, which leverages available measurement data to quantify whether the dynamic system performs as expected. We show that the surprise index can be computed in closed form for dynamic systems when observed evidence in a probabilistic model if the joint distribution for that evidence follows a multivariate Gaussian marginal distribution. We then apply it to a nonlinear spacecraft maneuver problem, where actions are chosen by a reinforcement learning agent and show it can indicate how well the trajectory follows the required orbit.
