FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4207021923> ?p ?o ?g. }

• W4207021923 endingPage "20" @default.
• W4207021923 startingPage "11" @default.
• W4207021923 abstract "According to cognitive psychology and related disciplines, the development of complex problem-solving behaviour in biological agents depends on hierarchical cognitive mechanisms. Hierarchical reinforcement learning is a promising computational approach that may eventually yield comparable problem-solving behaviour in artificial agents and robots. However, so far, the problem-solving abilities of many human and non-human animals are clearly superior to those of artificial systems. Here we propose steps to integrate biologically inspired hierarchical mechanisms to enable advanced problem-solving skills in artificial agents. We first review the literature in cognitive psychology to highlight the importance of compositional abstraction and predictive processing. Then we relate the gained insights with contemporary hierarchical reinforcement learning methods. Interestingly, our results suggest that all identified cognitive mechanisms have been implemented individually in isolated computational architectures, raising the question of why there exists no single unifying architecture that integrates them. As our final contribution, we address this question by providing an integrative perspective on the computational challenges to develop such a unifying architecture. We expect our results to guide the development of more sophisticated cognitively inspired hierarchical machine learning architectures. Although artificial reinforcement learning agents do well when rules are rigid, such as games, they fare poorly in real-world scenarios where small changes in the environment or the required actions can impair performance. The authors provide an overview of the cognitive foundations of hierarchical problem-solving, and propose steps to integrate biologically inspired hierarchical mechanisms to enable problem-solving skills in artificial agents." @default.
• W4207021923 created "2022-01-26" @default.
• W4207021923 creator A5033486668 @default.
• W4207021923 creator A5040045142 @default.
• W4207021923 creator A5050108731 @default.
• W4207021923 creator A5075919503 @default.
• W4207021923 creator A5077148400 @default.
• W4207021923 creator A5090767927 @default.
• W4207021923 date "2022-01-25" @default.
• W4207021923 modified "2023-10-14" @default.
• W4207021923 title "Intelligent problem-solving as integrated hierarchical reinforcement learning" @default.
• W4207021923 cites W1491843047 @default.
• W4207021923 cites W1498788589 @default.
• W4207021923 cites W1516436026 @default.
• W4207021923 cites W1520597402 @default.
• W4207021923 cites W1967627760 @default.
• W4207021923 cites W1976715276 @default.
• W4207021923 cites W1978169518 @default.
• W4207021923 cites W1982786963 @default.
• W4207021923 cites W1988699227 @default.
• W4207021923 cites W1989616852 @default.
• W4207021923 cites W1990640430 @default.
• W4207021923 cites W2009353347 @default.
• W4207021923 cites W2019455361 @default.
• W4207021923 cites W2023722569 @default.
• W4207021923 cites W2028143763 @default.
• W4207021923 cites W2034806191 @default.
• W4207021923 cites W2035090004 @default.
• W4207021923 cites W2059320470 @default.
• W4207021923 cites W2074407457 @default.
• W4207021923 cites W2091634289 @default.
• W4207021923 cites W2101143083 @default.
• W4207021923 cites W2101524054 @default.
• W4207021923 cites W2103359390 @default.
• W4207021923 cites W2105797824 @default.
• W4207021923 cites W2109910161 @default.
• W4207021923 cites W2111947800 @default.
• W4207021923 cites W2112874374 @default.
• W4207021923 cites W2113122939 @default.
• W4207021923 cites W2132003317 @default.
• W4207021923 cites W2133105703 @default.
• W4207021923 cites W2141086994 @default.
• W4207021923 cites W2147357263 @default.
• W4207021923 cites W2148764920 @default.
• W4207021923 cites W2153791616 @default.
• W4207021923 cites W2154562678 @default.
• W4207021923 cites W2160269795 @default.
• W4207021923 cites W2172084161 @default.
• W4207021923 cites W2470855507 @default.
• W4207021923 cites W2522489477 @default.
• W4207021923 cites W2526753222 @default.
• W4207021923 cites W2604213794 @default.
• W4207021923 cites W2730274928 @default.
• W4207021923 cites W2774021370 @default.
• W4207021923 cites W2791797404 @default.
• W4207021923 cites W2805883505 @default.
• W4207021923 cites W2808558823 @default.
• W4207021923 cites W2892266804 @default.
• W4207021923 cites W2899455150 @default.
• W4207021923 cites W2899685447 @default.
• W4207021923 cites W2913211608 @default.
• W4207021923 cites W2919912236 @default.
• W4207021923 cites W2920329255 @default.
• W4207021923 cites W2958112174 @default.
• W4207021923 cites W2963523627 @default.
• W4207021923 cites W2963709735 @default.
• W4207021923 cites W2964118262 @default.
• W4207021923 cites W2964227312 @default.
• W4207021923 cites W2964262254 @default.
• W4207021923 cites W2964505566 @default.
• W4207021923 cites W2974979868 @default.
• W4207021923 cites W2990118443 @default.
• W4207021923 cites W2998875866 @default.
• W4207021923 cites W3000554410 @default.
• W4207021923 cites W3014928460 @default.
• W4207021923 cites W3017262417 @default.
• W4207021923 cites W3034327502 @default.
• W4207021923 cites W3040518754 @default.
• W4207021923 cites W3096807772 @default.
• W4207021923 cites W3100789280 @default.
• W4207021923 cites W4206698690 @default.
• W4207021923 cites W4212793374 @default.
• W4207021923 cites W4212844288 @default.
• W4207021923 cites W4230449744 @default.
• W4207021923 cites W4241976975 @default.
• W4207021923 cites W4242883546 @default.
• W4207021923 cites W4246139359 @default.
• W4207021923 cites W4246203483 @default.
• W4207021923 cites W4246799520 @default.
• W4207021923 cites W4249742433 @default.
• W4207021923 doi "https://doi.org/10.1038/s42256-021-00433-9" @default.
• W4207021923 hasPublicationYear "2022" @default.
• W4207021923 type Work @default.
• W4207021923 citedByCount "22" @default.
• W4207021923 countsByYear W42070219232022 @default.
• W4207021923 countsByYear W42070219232023 @default.
• W4207021923 crossrefType "journal-article" @default.
• W4207021923 hasAuthorship W4207021923A5033486668 @default.

• next