Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952391987> ?p ?o ?g. }
- W2952391987 abstract "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 in its size, just as Thomas Malthus argued in 1798 was the relationship between preindustrial income levels and population growth. 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." @default.
- W2952391987 created "2019-06-27" @default.
- W2952391987 creator A5006947993 @default.
- W2952391987 creator A5033557144 @default.
- W2952391987 creator A5046100176 @default.
- W2952391987 creator A5051619646 @default.
- W2952391987 creator A5054808675 @default.
- W2952391987 creator A5056707583 @default.
- W2952391987 creator A5061221525 @default.
- W2952391987 creator A5082222209 @default.
- W2952391987 creator A5089479740 @default.
- W2952391987 date "2018-12-17" @default.
- W2952391987 modified "2023-10-02" @default.
- W2952391987 title "Malthusian Reinforcement Learning" @default.
- W2952391987 cites W1536166584 @default.
- W2952391987 cites W1591713425 @default.
- W2952391987 cites W1607114424 @default.
- W2952391987 cites W1982593017 @default.
- W2952391987 cites W1999363318 @default.
- W2952391987 cites W1999798677 @default.
- W2952391987 cites W2007802209 @default.
- W2952391987 cites W2029733813 @default.
- W2952391987 cites W2034806191 @default.
- W2952391987 cites W2036024839 @default.
- W2952391987 cites W2041367235 @default.
- W2952391987 cites W2063549544 @default.
- W2952391987 cites W2064675550 @default.
- W2952391987 cites W2069729948 @default.
- W2952391987 cites W2074028900 @default.
- W2952391987 cites W2086687204 @default.
- W2952391987 cites W2101493843 @default.
- W2952391987 cites W2119717200 @default.
- W2952391987 cites W2125393387 @default.
- W2952391987 cites W2138427174 @default.
- W2952391987 cites W2139612737 @default.
- W2952391987 cites W2149212390 @default.
- W2952391987 cites W2167287869 @default.
- W2952391987 cites W2257979135 @default.
- W2952391987 cites W2289312534 @default.
- W2952391987 cites W2330349018 @default.
- W2952391987 cites W2596982695 @default.
- W2952391987 cites W2663108269 @default.
- W2952391987 cites W2726727898 @default.
- W2952391987 cites W2751973545 @default.
- W2952391987 cites W2762117857 @default.
- W2952391987 cites W2772709170 @default.
- W2952391987 cites W2803005587 @default.
- W2952391987 cites W2810602713 @default.
- W2952391987 cites W2885550588 @default.
- W2952391987 cites W2895921264 @default.
- W2952391987 cites W2963276097 @default.
- W2952391987 cites W2963790038 @default.
- W2952391987 cites W2963985863 @default.
- W2952391987 cites W2964043796 @default.
- W2952391987 hasPublicationYear "2018" @default.
- W2952391987 type Work @default.
- W2952391987 sameAs 2952391987 @default.
- W2952391987 citedByCount "2" @default.
- W2952391987 countsByYear W29523919872019 @default.
- W2952391987 countsByYear W29523919872020 @default.
- W2952391987 crossrefType "posted-content" @default.
- W2952391987 hasAuthorship W2952391987A5006947993 @default.
- W2952391987 hasAuthorship W2952391987A5033557144 @default.
- W2952391987 hasAuthorship W2952391987A5046100176 @default.
- W2952391987 hasAuthorship W2952391987A5051619646 @default.
- W2952391987 hasAuthorship W2952391987A5054808675 @default.
- W2952391987 hasAuthorship W2952391987A5056707583 @default.
- W2952391987 hasAuthorship W2952391987A5061221525 @default.
- W2952391987 hasAuthorship W2952391987A5082222209 @default.
- W2952391987 hasAuthorship W2952391987A5089479740 @default.
- W2952391987 hasConcept C11413529 @default.
- W2952391987 hasConcept C144024400 @default.
- W2952391987 hasConcept C149923435 @default.
- W2952391987 hasConcept C154945302 @default.
- W2952391987 hasConcept C15744967 @default.
- W2952391987 hasConcept C162324750 @default.
- W2952391987 hasConcept C2908647359 @default.
- W2952391987 hasConcept C34447519 @default.
- W2952391987 hasConcept C41008148 @default.
- W2952391987 hasConcept C48103436 @default.
- W2952391987 hasConcept C67203356 @default.
- W2952391987 hasConcept C77352025 @default.
- W2952391987 hasConcept C77805123 @default.
- W2952391987 hasConcept C97541855 @default.
- W2952391987 hasConcept C994546 @default.
- W2952391987 hasConceptScore W2952391987C11413529 @default.
- W2952391987 hasConceptScore W2952391987C144024400 @default.
- W2952391987 hasConceptScore W2952391987C149923435 @default.
- W2952391987 hasConceptScore W2952391987C154945302 @default.
- W2952391987 hasConceptScore W2952391987C15744967 @default.
- W2952391987 hasConceptScore W2952391987C162324750 @default.
- W2952391987 hasConceptScore W2952391987C2908647359 @default.
- W2952391987 hasConceptScore W2952391987C34447519 @default.
- W2952391987 hasConceptScore W2952391987C41008148 @default.
- W2952391987 hasConceptScore W2952391987C48103436 @default.
- W2952391987 hasConceptScore W2952391987C67203356 @default.
- W2952391987 hasConceptScore W2952391987C77352025 @default.
- W2952391987 hasConceptScore W2952391987C77805123 @default.
- W2952391987 hasConceptScore W2952391987C97541855 @default.
- W2952391987 hasConceptScore W2952391987C994546 @default.