A research lab for self-learning systems
Self-learning beginswhen experience becomesmore than memory.
We study how autonomous systems turn interaction into self-learning: forming working hypotheses, testing them through action, and carrying forward what the evidence can support.
A task can end before learning begins
Completion is not learning.
A self-learning system must become different because it acted—more capable where experience holds, less certain where it does not, and ready to revise both.
act→observe→test→revise→transfer
Questions in progress
What would self-learning require?
01Learning from interaction
02Revising beliefs with evidence
03Transferring across encounters
Self-learningMemory & transfer
Memory is not yet learning
Remembering preserves experience. Self-learning must decide what the experience means—and whether it should change the next attempt.
Research questionsAdaptive systems
What changes after the first attempt?
A research agenda for agents that form hypotheses, test them through action, and revise what they carry forward.