Matches in SemOpenAlex for { <https://semopenalex.org/work/W2285495929> ?p ?o ?g. }
- W2285495929 abstract "Sequential decision making problems often require an agent to act in an environment where data is noisy or not fully observed. The agent will have to learn how different actions relate to different rewards, and must therefore balance the need to explore and exploit in an effective strategy. In this report, sequential decision making problems are considered through extensions of the multi-armed bandit framework. Firstly, the bandit problem is extended to a Multi-Agent System (MAS), where agents control individual arms but can communicate potentially useful information with each other. This framework allows for a better understanding of the exploration-exploitation tradeoff in scenarios where there are multiple agents interacting in a noisy environment. To this end, we present a novel strategy for action and communication decisions and we demonstrate the benefits of such a strategy empirically. This motivates a theoretical analysis of one-armed bandit problems, to develop ideas of how different strategies are optimally tuned. Specifically, the expected rewards of e-greedy strategies are derived, as well as proofs governing their optimal tuning." @default.
- W2285495929 created "2016-06-24" @default.
- W2285495929 creator A5026098176 @default.
- W2285495929 date "2011-04-01" @default.
- W2285495929 modified "2023-09-26" @default.
- W2285495929 title "The exploration-exploitation trade-off in sequential decision making problems" @default.
- W2285495929 cites W104909430 @default.
- W2285495929 cites W109262341 @default.
- W2285495929 cites W1487023704 @default.
- W2285495929 cites W1492221128 @default.
- W2285495929 cites W1504352750 @default.
- W2285495929 cites W1514325590 @default.
- W2285495929 cites W1515933446 @default.
- W2285495929 cites W1516061453 @default.
- W2285495929 cites W1517514910 @default.
- W2285495929 cites W1517897437 @default.
- W2285495929 cites W1532421987 @default.
- W2285495929 cites W1534277359 @default.
- W2285495929 cites W1538918057 @default.
- W2285495929 cites W1542941925 @default.
- W2285495929 cites W1547069917 @default.
- W2285495929 cites W1564229172 @default.
- W2285495929 cites W1569296262 @default.
- W2285495929 cites W1570963478 @default.
- W2285495929 cites W1580557482 @default.
- W2285495929 cites W158205031 @default.
- W2285495929 cites W1582436621 @default.
- W2285495929 cites W1591803298 @default.
- W2285495929 cites W1595351358 @default.
- W2285495929 cites W1598539741 @default.
- W2285495929 cites W1605188341 @default.
- W2285495929 cites W1625390266 @default.
- W2285495929 cites W1640358294 @default.
- W2285495929 cites W166250193 @default.
- W2285495929 cites W1672284634 @default.
- W2285495929 cites W1700100050 @default.
- W2285495929 cites W1826381381 @default.
- W2285495929 cites W1861050369 @default.
- W2285495929 cites W1906698607 @default.
- W2285495929 cites W1908253641 @default.
- W2285495929 cites W1917528016 @default.
- W2285495929 cites W1931792391 @default.
- W2285495929 cites W1940989903 @default.
- W2285495929 cites W1964500506 @default.
- W2285495929 cites W1964839117 @default.
- W2285495929 cites W1966347268 @default.
- W2285495929 cites W1977823770 @default.
- W2285495929 cites W1979540602 @default.
- W2285495929 cites W1987011264 @default.
- W2285495929 cites W1988360637 @default.
- W2285495929 cites W1995945562 @default.
- W2285495929 cites W1996859119 @default.
- W2285495929 cites W1998498767 @default.
- W2285495929 cites W2002985443 @default.
- W2285495929 cites W2004001705 @default.
- W2285495929 cites W2004971231 @default.
- W2285495929 cites W2005311763 @default.
- W2285495929 cites W2006733863 @default.
- W2285495929 cites W2009551863 @default.
- W2285495929 cites W2011065519 @default.
- W2285495929 cites W2018469926 @default.
- W2285495929 cites W2021622496 @default.
- W2285495929 cites W2029832535 @default.
- W2285495929 cites W2030729276 @default.
- W2285495929 cites W2031768652 @default.
- W2285495929 cites W2037436072 @default.
- W2285495929 cites W2039522160 @default.
- W2285495929 cites W2043962114 @default.
- W2285495929 cites W2045097767 @default.
- W2285495929 cites W2047273712 @default.
- W2285495929 cites W2049633694 @default.
- W2285495929 cites W2056921512 @default.
- W2285495929 cites W2057667118 @default.
- W2285495929 cites W2059571939 @default.
- W2285495929 cites W2065398693 @default.
- W2285495929 cites W2067399933 @default.
- W2285495929 cites W2072878407 @default.
- W2285495929 cites W2075665712 @default.
- W2285495929 cites W2076337359 @default.
- W2285495929 cites W2077902449 @default.
- W2285495929 cites W2088956500 @default.
- W2285495929 cites W2097487180 @default.
- W2285495929 cites W2101046777 @default.
- W2285495929 cites W2102365703 @default.
- W2285495929 cites W2102557862 @default.
- W2285495929 cites W2103561211 @default.
- W2285495929 cites W2103715332 @default.
- W2285495929 cites W2104389751 @default.
- W2285495929 cites W2104602264 @default.
- W2285495929 cites W2107726111 @default.
- W2285495929 cites W2107822634 @default.
- W2285495929 cites W2108114251 @default.
- W2285495929 cites W2108260662 @default.
- W2285495929 cites W2109100253 @default.
- W2285495929 cites W2112420033 @default.
- W2285495929 cites W2115519224 @default.
- W2285495929 cites W2118994458 @default.
- W2285495929 cites W2120846115 @default.
- W2285495929 cites W2121667311 @default.
- W2285495929 cites W2121863487 @default.