简介:Aprimarychallengeofagent-basedpolicylearningincomplexanduncertainenvironmentsisescalatingcomputationalcomplexitywiththesizeofthetaskspace(actionchoicesandworldstates)andthenumberofagents.Nonetheless,thereisampleevidenceinthenaturalworldthathigh-functioningsocialmammalslearntosolvecomplexproblemswithease,bothindividuallyandcooperatively.Thisabilitytosolvecomputationallyintractableproblemsstemsfrombothbraincircuitsforhierarchicalrepresentation...