AI RESEARCH
MC-CPO: Mastery-Conditioned Constrained Policy Optimization
arXiv CS.AI
•
ArXi:2604.04251v1 Announce Type: new Engagement-optimized adaptive tutoring systems may prioritize short-term behavioral signals over sustained learning outcomes, creating structural incentives for reward hacking in reinforcement learning policies. We formalize this challenge as a constrained Marko decision process (CMDP) with mastery-conditioned feasibility, in which pedagogical safety constraints dynamically restrict admissible actions according to learner mastery and prerequisite structure.