Matches in SemOpenAlex for { <https://semopenalex.org/work/W2014394432> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2014394432 endingPage "297" @default.
- W2014394432 startingPage "286" @default.
- W2014394432 abstract "Following work on designing optimal rewards for single agents, we define a multiagent optimal rewards problem (ORP) in cooperative (specifically, common-payoff or team) settings. This new problem solves for individual agent reward functions that guide agents to better overall team performance relative to teams in which all agents guide their behavior with the same given team-reward function. We present a multiagent architecture in which each agent learns good reward functions from experience using a gradient-based algorithm in addition to performing the usual task of planning good policies (except in this case with respect to the learned rather than the given reward function). Multiagency introduces the challenge of nonstationarity: because the agents learn simultaneously, each agent's reward-learning problem is nonstationary and interdependent on the other agents evolving reward functions. We demonstrate on two simple domains that the proposed architecture outperforms the conventional approach in which all the agents use the same given team-reward function (even when accounting for the resource overhead of the reward learning); that the learning algorithm performs stably despite the nonstationarity; and that learning individual reward functions can lead to better specialization of roles than is possible with shared reward, whether learned or given." @default.
- W2014394432 created "2016-06-24" @default.
- W2014394432 creator A5003698008 @default.
- W2014394432 creator A5058280770 @default.
- W2014394432 creator A5065366930 @default.
- W2014394432 creator A5077109450 @default.
- W2014394432 date "2014-12-01" @default.
- W2014394432 modified "2023-09-27" @default.
- W2014394432 title "Optimal Rewards for Cooperative Agents" @default.
- W2014394432 cites W1625390266 @default.
- W2014394432 cites W1819200667 @default.
- W2014394432 cites W1863227302 @default.
- W2014394432 cites W1975744985 @default.
- W2014394432 cites W2000514530 @default.
- W2014394432 cites W2071841410 @default.
- W2014394432 cites W2101524054 @default.
- W2014394432 cites W2105546430 @default.
- W2014394432 cites W2122480991 @default.
- W2014394432 cites W2123408238 @default.
- W2014394432 cites W2127572219 @default.
- W2014394432 cites W2154902490 @default.
- W2014394432 cites W2155511972 @default.
- W2014394432 cites W2164424353 @default.
- W2014394432 cites W2168405694 @default.
- W2014394432 cites W2896027395 @default.
- W2014394432 cites W807910218 @default.
- W2014394432 doi "https://doi.org/10.1109/tamd.2014.2362682" @default.
- W2014394432 hasPublicationYear "2014" @default.
- W2014394432 type Work @default.
- W2014394432 sameAs 2014394432 @default.
- W2014394432 citedByCount "13" @default.
- W2014394432 countsByYear W20143944322016 @default.
- W2014394432 countsByYear W20143944322017 @default.
- W2014394432 countsByYear W20143944322018 @default.
- W2014394432 countsByYear W20143944322019 @default.
- W2014394432 countsByYear W20143944322020 @default.
- W2014394432 countsByYear W20143944322021 @default.
- W2014394432 countsByYear W20143944322022 @default.
- W2014394432 countsByYear W20143944322023 @default.
- W2014394432 crossrefType "journal-article" @default.
- W2014394432 hasAuthorship W2014394432A5003698008 @default.
- W2014394432 hasAuthorship W2014394432A5058280770 @default.
- W2014394432 hasAuthorship W2014394432A5065366930 @default.
- W2014394432 hasAuthorship W2014394432A5077109450 @default.
- W2014394432 hasConcept C119857082 @default.
- W2014394432 hasConcept C127413603 @default.
- W2014394432 hasConcept C14036430 @default.
- W2014394432 hasConcept C144237770 @default.
- W2014394432 hasConcept C154945302 @default.
- W2014394432 hasConcept C17744445 @default.
- W2014394432 hasConcept C185874996 @default.
- W2014394432 hasConcept C199539241 @default.
- W2014394432 hasConcept C201995342 @default.
- W2014394432 hasConcept C22171661 @default.
- W2014394432 hasConcept C2780451532 @default.
- W2014394432 hasConcept C33923547 @default.
- W2014394432 hasConcept C41008148 @default.
- W2014394432 hasConcept C78458016 @default.
- W2014394432 hasConcept C86803240 @default.
- W2014394432 hasConceptScore W2014394432C119857082 @default.
- W2014394432 hasConceptScore W2014394432C127413603 @default.
- W2014394432 hasConceptScore W2014394432C14036430 @default.
- W2014394432 hasConceptScore W2014394432C144237770 @default.
- W2014394432 hasConceptScore W2014394432C154945302 @default.
- W2014394432 hasConceptScore W2014394432C17744445 @default.
- W2014394432 hasConceptScore W2014394432C185874996 @default.
- W2014394432 hasConceptScore W2014394432C199539241 @default.
- W2014394432 hasConceptScore W2014394432C201995342 @default.
- W2014394432 hasConceptScore W2014394432C22171661 @default.
- W2014394432 hasConceptScore W2014394432C2780451532 @default.
- W2014394432 hasConceptScore W2014394432C33923547 @default.
- W2014394432 hasConceptScore W2014394432C41008148 @default.
- W2014394432 hasConceptScore W2014394432C78458016 @default.
- W2014394432 hasConceptScore W2014394432C86803240 @default.
- W2014394432 hasIssue "4" @default.
- W2014394432 hasLocation W20143944321 @default.
- W2014394432 hasOpenAccess W2014394432 @default.
- W2014394432 hasPrimaryLocation W20143944321 @default.
- W2014394432 hasRelatedWork W1981558224 @default.
- W2014394432 hasRelatedWork W2081647779 @default.
- W2014394432 hasRelatedWork W2095876242 @default.
- W2014394432 hasRelatedWork W2961085424 @default.
- W2014394432 hasRelatedWork W3046775127 @default.
- W2014394432 hasRelatedWork W4285260836 @default.
- W2014394432 hasRelatedWork W4286629047 @default.
- W2014394432 hasRelatedWork W4306321456 @default.
- W2014394432 hasRelatedWork W4306674287 @default.
- W2014394432 hasRelatedWork W4224009465 @default.
- W2014394432 hasVolume "6" @default.
- W2014394432 isParatext "false" @default.
- W2014394432 isRetracted "false" @default.
- W2014394432 magId "2014394432" @default.
- W2014394432 workType "article" @default.