Conformal Off-Policy Prediction for Multi-Agent Systems

arXiv:2403.16871v1 Announce Type: cross
Abstract: Off-Policy Prediction (OPP), i.e., predicting the outcomes of a target policy using only data collected under a nominal (behavioural) policy, is a paramount problem in data-driven analysis of safety-critical systems where the deployment of a new policy may be unsafe. To achieve dependable off-policy predictions, recent work on Conformal Off-Policy Prediction (COPP) leverage the conformal prediction framework to derive prediction regions with probabilistic guarantees under the target process. Existing COPP methods can account for the …

abstract agent analysis arxiv cs.lg cs.ma data data-driven deployment multi-agent policy prediction predictions safety safety-critical stat.ml systems type work