Here we explore a new algorithmic framework for multi-agent reinforcement learning, called Malthusian reinforcement learning, which extends self-play to include fitness-linked population size dynamics that drive ongoing innovation. In Malthusian RL, increases in a subpopulation’s average return drive subsequent increases inits size, just as Thomas Malthus argued in 1798 was the relationship between preindustrial income levels and population growth [24]. Malthusian reinforcement learning harnesses the competitive pressures arising from growing and shrinking population size to drive agents to explore regions of state and policy spaces that they could not otherwise reach. Furthermore, in environments where there are potential gains from specialization and division of labor, we show that Malthusian reinforcement learning is better positioned to take advantage of such synergies than algorithms based on self-play.


    Access

    Download


    Export, share and cite



    Title :

    Malthusian Reinforcement Learning


    Contributors:

    Publication date :

    2019-05-17


    Remarks:

    In: Elkind, Edith and Veloso, Manuela, (eds.) Proceedings of the 18th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2019). (pp. pp. 1099-1107). IFAAMAS (International Foundation of Autonomous Agents and MultiAgent Systems): Montreal, Canada. (2019)


    Type of media :

    Paper


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629



    Fast Lane - Malthusian Motoring.

    Online Contents | 2004


    Minimax Reinforcement Learning

    Chakravorty, Suman / Hyland, David | AIAA | 2003


    Deep Reinforcement Learning

    Huang, Xiaowei / Jin, Gaojie / Ruan, Wenjie | Springer Verlag | 2012


    SAFE AND EFFICIENT REINFORCEMENT LEARNING ; Säker och effektiv reinforcement learning

    Magnusson, Björn / Forslund, Måns | BASE | 2019

    Free access