This paper illustrates a 10-year research endeavor on collective learning, a paradigm for tackling tragedy of the commons problems in socio-technical systems using human-centered distributed intelligence. In contrast to mainstream centralized artificial intelligence (AI) allowing algorithmic discrimination and manipulative nudging, the decentralized approach of collective learning is by-design participatory and value-sensitive: it aligns with privacy, autonomy, fairness and democratic values. Engineering such values in a socio-technical system results in computational constraints that turn collective decision-making into complex combinatorial NP-hard problems. These are the problems that collective learning and the EPOS research project tackles. Collective learning finds striking applicability in energy, traffic, supply-chain and the self-management of sharing economies. This grand applicability and the social impact are demonstrated in this paper along with a future perspective of the collective learning paradigm.