Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367694568> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4367694568 abstract "A central problem in the theory of multi-agent reinforcement learning (MARL) is to understand what structural conditions and algorithmic principles lead to sample-efficient learning guarantees, and how these considerations change as we move from few to many agents. We study this question in a general framework for interactive decision making with multiple agents, encompassing Markov games with function approximation and normal-form games with bandit feedback. We focus on equilibrium computation, in which a centralized learning algorithm aims to compute an equilibrium by controlling multiple agents that interact with an unknown environment. Our main contributions are: - We provide upper and lower bounds on the optimal sample complexity for multi-agent decision making based on a multi-agent generalization of the Decision-Estimation Coefficient, a complexity measure introduced by Foster et al. (2021) in the single-agent counterpart to our setting. Compared to the best results for the single-agent setting, our bounds have additional gaps. We show that no reasonable complexity measure can close these gaps, highlighting a striking separation between single and multiple agents. - We show that characterizing the statistical complexity for multi-agent decision making is equivalent to characterizing the statistical complexity of single-agent decision making, but with hidden (unobserved) rewards, a framework that subsumes variants of the partial monitoring problem. As a consequence, we characterize the statistical complexity for hidden-reward interactive decision making to the best extent possible. Building on this development, we provide several new structural results, including 1) conditions under which the statistical complexity of multi-agent decision making can be reduced to that of single-agent, and 2) conditions under which the so-called curse of multiple agents can be avoided." @default.
- W4367694568 created "2023-05-03" @default.
- W4367694568 creator A5002177720 @default.
- W4367694568 creator A5075069827 @default.
- W4367694568 creator A5076656836 @default.
- W4367694568 creator A5089252105 @default.
- W4367694568 date "2023-05-01" @default.
- W4367694568 modified "2023-10-18" @default.
- W4367694568 title "On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring" @default.
- W4367694568 doi "https://doi.org/10.48550/arxiv.2305.00684" @default.
- W4367694568 hasPublicationYear "2023" @default.
- W4367694568 type Work @default.
- W4367694568 citedByCount "0" @default.
- W4367694568 crossrefType "posted-content" @default.
- W4367694568 hasAuthorship W4367694568A5002177720 @default.
- W4367694568 hasAuthorship W4367694568A5075069827 @default.
- W4367694568 hasAuthorship W4367694568A5076656836 @default.
- W4367694568 hasAuthorship W4367694568A5089252105 @default.
- W4367694568 hasBestOaLocation W43676945681 @default.
- W4367694568 hasConcept C105795698 @default.
- W4367694568 hasConcept C106189395 @default.
- W4367694568 hasConcept C11413529 @default.
- W4367694568 hasConcept C115988155 @default.
- W4367694568 hasConcept C119857082 @default.
- W4367694568 hasConcept C124101348 @default.
- W4367694568 hasConcept C126255220 @default.
- W4367694568 hasConcept C134306372 @default.
- W4367694568 hasConcept C14036430 @default.
- W4367694568 hasConcept C154945302 @default.
- W4367694568 hasConcept C159886148 @default.
- W4367694568 hasConcept C177148314 @default.
- W4367694568 hasConcept C179799912 @default.
- W4367694568 hasConcept C2778445095 @default.
- W4367694568 hasConcept C2780009758 @default.
- W4367694568 hasConcept C33923547 @default.
- W4367694568 hasConcept C41008148 @default.
- W4367694568 hasConcept C78458016 @default.
- W4367694568 hasConcept C86803240 @default.
- W4367694568 hasConcept C97541855 @default.
- W4367694568 hasConceptScore W4367694568C105795698 @default.
- W4367694568 hasConceptScore W4367694568C106189395 @default.
- W4367694568 hasConceptScore W4367694568C11413529 @default.
- W4367694568 hasConceptScore W4367694568C115988155 @default.
- W4367694568 hasConceptScore W4367694568C119857082 @default.
- W4367694568 hasConceptScore W4367694568C124101348 @default.
- W4367694568 hasConceptScore W4367694568C126255220 @default.
- W4367694568 hasConceptScore W4367694568C134306372 @default.
- W4367694568 hasConceptScore W4367694568C14036430 @default.
- W4367694568 hasConceptScore W4367694568C154945302 @default.
- W4367694568 hasConceptScore W4367694568C159886148 @default.
- W4367694568 hasConceptScore W4367694568C177148314 @default.
- W4367694568 hasConceptScore W4367694568C179799912 @default.
- W4367694568 hasConceptScore W4367694568C2778445095 @default.
- W4367694568 hasConceptScore W4367694568C2780009758 @default.
- W4367694568 hasConceptScore W4367694568C33923547 @default.
- W4367694568 hasConceptScore W4367694568C41008148 @default.
- W4367694568 hasConceptScore W4367694568C78458016 @default.
- W4367694568 hasConceptScore W4367694568C86803240 @default.
- W4367694568 hasConceptScore W4367694568C97541855 @default.
- W4367694568 hasLocation W43676945681 @default.
- W4367694568 hasOpenAccess W4367694568 @default.
- W4367694568 hasPrimaryLocation W43676945681 @default.
- W4367694568 hasRelatedWork W2765742413 @default.
- W4367694568 hasRelatedWork W2989932438 @default.
- W4367694568 hasRelatedWork W3049166411 @default.
- W4367694568 hasRelatedWork W3213838085 @default.
- W4367694568 hasRelatedWork W3215473757 @default.
- W4367694568 hasRelatedWork W4226218429 @default.
- W4367694568 hasRelatedWork W4285605464 @default.
- W4367694568 hasRelatedWork W4287688416 @default.
- W4367694568 hasRelatedWork W4313591620 @default.
- W4367694568 hasRelatedWork W4320813994 @default.
- W4367694568 isParatext "false" @default.
- W4367694568 isRetracted "false" @default.
- W4367694568 workType "article" @default.