AI RESEARCH
Matrix-Space Reinforcement Learning for Reusing Local Transition Geometry
arXiv CS.LG
•
ArXi:2605.14304v1 Announce Type: new Compositional generalization in sequential decision-making requires identifying which parts of prior rollouts remain useful for new tasks. Existing methods reuse skills or predictive models, but often overlook rich local transition geometry and dynamics. We propose Matrix-Space Reinforcement Learning (MSRL), a geometric abstraction that represents trajectory segments through positive semidefinite matrix descriptors aggregating first- and second-order statistics of lifted one-step transitions.