A Computational Theory for Efficient Mini Agent Evaluation with Causal Guarantees

Hedong Yan

Keywords: causal learning, computational evaluation, causal-prediction connection, mini agent

TL;DR: Use computational model to accelerate the evaluation process with siginicant lower errors; Prove upper bound of generalized error and generalized causal effect error of any unbiased prediction model to solve non-positivity.

Abstract: In order to reduce the cost of experimental evaluation for agents, we introduce a computational theory of evaluation for mini agents: build evaluation model to accelerate the evaluation procedures. We prove upper bounds of generalized error and generalized causal effect error of given evaluation models for infinite agents. We also prove efficiency, and consistency to estimated causal effect from deployed agents to evaluation metric by prediction. To learn evaluation models, we propose a meta-learner to handle heterogeneous agents space problem. Comparing with existed evaluation approaches, our (conditional) evaluation model reduced 24.1\% to 99.0\% evaluation errors across 12 scenes, including individual medicine, scientific simulation, social experiment, business activity, and quantum trade. The evaluation time is reduced 3 to 7 order of magnitude comparing with experiments or simulations.

Primary Area: Evaluation (e.g., methodology, meta studies, replicability and validity, human-in-the-loop)

Submission Number: 2941