FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3138460475> ?p ?o ?g. }

• W3138460475 abstract "Multi-agent reinforcement learning (MARL) has become effective in tackling discrete cooperative game scenarios. However, MARL has yet to penetrate settings beyond those modelled by team and zero-sum games, confining it to a small subset of multi-agent systems. In this paper, we introduce a new generation of MARL learners that can handle nonzero-sum payoff structures and continuous settings. In particular, we study the MARL problem in a class of games known as stochastic potential games (SPGs) with continuous state-action spaces. Unlike cooperative games, in which all agents share a common reward, SPGs are capable of modelling real-world scenarios where agents seek to fulfil their individual goals. We prove theoretically our learning method, SPot-AC, enables independent agents to learn Nash equilibrium strategies in polynomial time. We demonstrate our framework tackles previously unsolvable tasks such as Coordination Navigation and large selfish routing games and that it outperforms the state of the art MARL baselines such as MADDPG and COMIX in such scenarios." @default.
• W3138460475 created "2021-03-29" @default.
• W3138460475 creator A5002080576 @default.
• W3138460475 creator A5006156363 @default.
• W3138460475 creator A5012417955 @default.
• W3138460475 creator A5036563779 @default.
• W3138460475 creator A5042241049 @default.
• W3138460475 creator A5043644495 @default.
• W3138460475 creator A5054236046 @default.
• W3138460475 creator A5076637933 @default.
• W3138460475 creator A5090073634 @default.
• W3138460475 date "2021-03-16" @default.
• W3138460475 modified "2023-09-23" @default.
• W3138460475 title "Learning in Nonzero-Sum Stochastic Games with Potentials" @default.
• W3138460475 cites W1192553058 @default.
• W3138460475 cites W1519783625 @default.
• W3138460475 cites W1528676759 @default.
• W3138460475 cites W1576580777 @default.
• W3138460475 cites W1603289878 @default.
• W3138460475 cites W1641379095 @default.
• W3138460475 cites W1675187506 @default.
• W3138460475 cites W1971942712 @default.
• W3138460475 cites W2020677486 @default.
• W3138460475 cites W2026662445 @default.
• W3138460475 cites W2032100464 @default.
• W3138460475 cites W2034019401 @default.
• W3138460475 cites W2044212084 @default.
• W3138460475 cites W2057913812 @default.
• W3138460475 cites W2103151730 @default.
• W3138460475 cites W2118247617 @default.
• W3138460475 cites W2120846115 @default.
• W3138460475 cites W2121863487 @default.
• W3138460475 cites W2122689259 @default.
• W3138460475 cites W2128727659 @default.
• W3138460475 cites W2145067550 @default.
• W3138460475 cites W2151416233 @default.
• W3138460475 cites W2155027007 @default.
• W3138460475 cites W2156737235 @default.
• W3138460475 cites W2164300250 @default.
• W3138460475 cites W2165150801 @default.
• W3138460475 cites W2173248099 @default.
• W3138460475 cites W2263547296 @default.
• W3138460475 cites W2263699442 @default.
• W3138460475 cites W2295179707 @default.
• W3138460475 cites W2494628279 @default.
• W3138460475 cites W2565610523 @default.
• W3138460475 cites W2623431351 @default.
• W3138460475 cites W2740377041 @default.
• W3138460475 cites W2756196406 @default.
• W3138460475 cites W2783494847 @default.
• W3138460475 cites W2785915381 @default.
• W3138460475 cites W2786479217 @default.
• W3138460475 cites W2787270134 @default.
• W3138460475 cites W2883204331 @default.
• W3138460475 cites W2950776615 @default.
• W3138460475 cites W2951984055 @default.
• W3138460475 cites W2962938168 @default.
• W3138460475 cites W2963039558 @default.
• W3138460475 cites W2963116103 @default.
• W3138460475 cites W2963407617 @default.
• W3138460475 cites W2963605646 @default.
• W3138460475 cites W2964279665 @default.
• W3138460475 cites W2990725117 @default.
• W3138460475 cites W2997072274 @default.
• W3138460475 cites W3011672202 @default.
• W3138460475 cites W3093287223 @default.
• W3138460475 cites W3093963693 @default.
• W3138460475 cites W3107615218 @default.
• W3138460475 cites W3163926178 @default.
• W3138460475 cites W3169011731 @default.
• W3138460475 cites W3172288035 @default.
• W3138460475 cites W33871791 @default.
• W3138460475 cites W588228448 @default.
• W3138460475 hasPublicationYear "2021" @default.
• W3138460475 type Work @default.
• W3138460475 sameAs 3138460475 @default.
• W3138460475 citedByCount "2" @default.
• W3138460475 countsByYear W31384604752021 @default.
• W3138460475 crossrefType "posted-content" @default.
• W3138460475 hasAuthorship W3138460475A5002080576 @default.
• W3138460475 hasAuthorship W3138460475A5006156363 @default.
• W3138460475 hasAuthorship W3138460475A5012417955 @default.
• W3138460475 hasAuthorship W3138460475A5036563779 @default.
• W3138460475 hasAuthorship W3138460475A5042241049 @default.
• W3138460475 hasAuthorship W3138460475A5043644495 @default.
• W3138460475 hasAuthorship W3138460475A5054236046 @default.
• W3138460475 hasAuthorship W3138460475A5076637933 @default.
• W3138460475 hasAuthorship W3138460475A5090073634 @default.
• W3138460475 hasConcept C109007969 @default.
• W3138460475 hasConcept C11413529 @default.
• W3138460475 hasConcept C126255220 @default.
• W3138460475 hasConcept C136356330 @default.
• W3138460475 hasConcept C144237770 @default.
• W3138460475 hasConcept C151730666 @default.
• W3138460475 hasConcept C154945302 @default.
• W3138460475 hasConcept C177142836 @default.
• W3138460475 hasConcept C22171661 @default.
• W3138460475 hasConcept C2777212361 @default.
• W3138460475 hasConcept C2778079155 @default.
• W3138460475 hasConcept C33923547 @default.

• next