FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2980452497> ?p ?o ?g. }

• W2980452497 abstract "We study discrete-time mean-field Markov games with infinite numbers of agents where each agent aims to minimize its ergodic cost. We consider the setting where the agents have identical linear state transitions and quadratic cost functions, while the aggregated effect of the agents is captured by the population mean of their states, namely, the mean-field state. For such a game, based on the Nash certainty equivalence principle, we provide sufficient conditions for the existence and uniqueness of its Nash equilibrium. Moreover, to find the Nash equilibrium, we propose a mean-field actor-critic algorithm with linear function approximation, which does not require knowing the model of dynamics. Specifically, at each iteration of our algorithm, we use the single-agent actor-critic algorithm to approximately obtain the optimal policy of the each agent given the current mean-field state, and then update the mean-field state. In particular, we prove that our algorithm converges to the Nash equilibrium at a linear rate. To the best of our knowledge, this is the first success of applying model-free reinforcement learning with function approximation to discrete-time mean-field Markov games with provable non-asymptotic global convergence guarantees." @default.
• W2980452497 created "2019-10-25" @default.
• W2980452497 creator A5025567827 @default.
• W2980452497 creator A5048272675 @default.
• W2980452497 creator A5066940107 @default.
• W2980452497 creator A5078210646 @default.
• W2980452497 date "2019-10-16" @default.
• W2980452497 modified "2023-09-27" @default.
• W2980452497 title "Actor-Critic Provably Finds Nash Equilibria of Linear-Quadratic Mean-Field Games" @default.
• W2980452497 cites W1023560205 @default.
• W2980452497 cites W1480180679 @default.
• W2980452497 cites W1490782493 @default.
• W2980452497 cites W1499021337 @default.
• W2980452497 cites W1513468570 @default.
• W2980452497 cites W1519783625 @default.
• W2980452497 cites W1522531528 @default.
• W2980452497 cites W1542941925 @default.
• W2980452497 cites W1567092208 @default.
• W2980452497 cites W1569631138 @default.
• W2980452497 cites W1576577548 @default.
• W2980452497 cites W1616818660 @default.
• W2980452497 cites W1808956822 @default.
• W2980452497 cites W1821455959 @default.
• W2980452497 cites W182704713 @default.
• W2980452497 cites W1835254890 @default.
• W2980452497 cites W1971800148 @default.
• W2980452497 cites W1973258650 @default.
• W2980452497 cites W1983321045 @default.
• W2980452497 cites W1986431940 @default.
• W2980452497 cites W1989575809 @default.
• W2980452497 cites W1992169727 @default.
• W2980452497 cites W2002788332 @default.
• W2980452497 cites W2007617105 @default.
• W2980452497 cites W2011000015 @default.
• W2980452497 cites W2011435133 @default.
• W2980452497 cites W2012110988 @default.
• W2980452497 cites W2032291279 @default.
• W2980452497 cites W2035702014 @default.
• W2980452497 cites W2038686546 @default.
• W2980452497 cites W2041236557 @default.
• W2980452497 cites W2042407819 @default.
• W2980452497 cites W2052912377 @default.
• W2980452497 cites W2071983464 @default.
• W2980452497 cites W2075268401 @default.
• W2980452497 cites W2078363504 @default.
• W2980452497 cites W2087322096 @default.
• W2980452497 cites W2094387729 @default.
• W2980452497 cites W2099618002 @default.
• W2980452497 cites W2103437045 @default.
• W2980452497 cites W2103561211 @default.
• W2980452497 cites W2114585732 @default.
• W2980452497 cites W2120846115 @default.
• W2980452497 cites W2121832485 @default.
• W2980452497 cites W2121863487 @default.
• W2980452497 cites W2129695524 @default.
• W2980452497 cites W2129951390 @default.
• W2980452497 cites W2130801532 @default.
• W2980452497 cites W2141091023 @default.
• W2980452497 cites W2155027007 @default.
• W2980452497 cites W2156194062 @default.
• W2980452497 cites W2156737235 @default.
• W2980452497 cites W2165905123 @default.
• W2980452497 cites W2172968643 @default.
• W2980452497 cites W2243856001 @default.
• W2980452497 cites W2257979135 @default.
• W2980452497 cites W2291986326 @default.
• W2980452497 cites W2330024298 @default.
• W2980452497 cites W2345177722 @default.
• W2980452497 cites W2395162158 @default.
• W2980452497 cites W2413079700 @default.
• W2980452497 cites W2462023919 @default.
• W2980452497 cites W2521454744 @default.
• W2980452497 cites W2530299800 @default.
• W2980452497 cites W2530849036 @default.
• W2980452497 cites W2560316583 @default.
• W2980452497 cites W2569469264 @default.
• W2980452497 cites W2574978968 @default.
• W2980452497 cites W2594203335 @default.
• W2980452497 cites W2610414461 @default.
• W2980452497 cites W2737170301 @default.
• W2980452497 cites W2748414289 @default.
• W2980452497 cites W2749049902 @default.
• W2980452497 cites W2752423433 @default.
• W2980452497 cites W2761923184 @default.
• W2980452497 cites W2766447205 @default.
• W2980452497 cites W2767550855 @default.
• W2980452497 cites W2776728688 @default.
• W2980452497 cites W2776811469 @default.
• W2980452497 cites W2785315072 @default.
• W2980452497 cites W2788366696 @default.
• W2980452497 cites W2789382902 @default.
• W2980452497 cites W2791784110 @default.
• W2980452497 cites W2798534591 @default.
• W2980452497 cites W2799183551 @default.
• W2980452497 cites W2887625306 @default.
• W2980452497 cites W2888559564 @default.
• W2980452497 cites W2891661335 @default.
• W2980452497 cites W2893902012 @default.
• W2980452497 cites W2904058351 @default.
• W2980452497 cites W2911244894 @default.

• next