Matches in SemOpenAlex for { <https://semopenalex.org/work/W2102000945> ?p ?o ?g. }
- W2102000945 abstract "Learning, planning, and representing knowledge at multiple levels of temporal abstraction are key challenges for AI. In this paper we develop an approach to these problems based on the mathematical framework of reinforcement learning and Markov decision processes (MDPs). We extend the usual notion of action to include {em options/}---whole courses of behavior that may be temporally extended, stochastic, and contingent on events. Examples of options include picking up an object, going to lunch, and traveling to a distant city, as well as primitive actions such as muscle twitches or joint torques. Options may be given a priori, learned by experience, or both. They may be used interchangably with actions in a variety of planning and learning methods. The theory of semi-Markov decision processes (SMDPs) can be applied to model the consequences of options and to plan and learn with them. In this paper we develop these connections, building on prior work by Bradtke and Duff (1995), Parr (1998) and others. Our main novel results concern the interface between the MDP and SMDP levels of analysis. We show how a set of options can be altered by changing only their termination conditions to improve over SMDP methods with no additional cost. We also introduce {it intra-option/} temporal-difference methods that are able to learn from fragments of an option''s execution. Finally, we propose a notion of subgoal which can be used to improve the options themselves. Overall, we argue that options and their models provide hitherto missing aspects of a powerful, clear, and expressive framework for representing and organizing knowledge." @default.
- W2102000945 created "2016-06-24" @default.
- W2102000945 creator A5004923102 @default.
- W2102000945 creator A5065366930 @default.
- W2102000945 creator A5065836447 @default.
- W2102000945 date "1998-08-01" @default.
- W2102000945 modified "2023-10-11" @default.
- W2102000945 title "Between MOPs and Semi-MOP: Learning, Planning & Representing Knowledge at Multiple Temporal Scales" @default.
- W2102000945 cites W141456974 @default.
- W2102000945 cites W1488730473 @default.
- W2102000945 cites W1503515926 @default.
- W2102000945 cites W1503821144 @default.
- W2102000945 cites W1507087299 @default.
- W2102000945 cites W1562247642 @default.
- W2102000945 cites W1578485649 @default.
- W2102000945 cites W1592402337 @default.
- W2102000945 cites W1594216983 @default.
- W2102000945 cites W1595483645 @default.
- W2102000945 cites W1598634407 @default.
- W2102000945 cites W1600813180 @default.
- W2102000945 cites W1603565927 @default.
- W2102000945 cites W16046748 @default.
- W2102000945 cites W1612579644 @default.
- W2102000945 cites W1631187438 @default.
- W2102000945 cites W1699699942 @default.
- W2102000945 cites W1748123235 @default.
- W2102000945 cites W181115729 @default.
- W2102000945 cites W1815493548 @default.
- W2102000945 cites W18781575 @default.
- W2102000945 cites W1966028617 @default.
- W2102000945 cites W1966195676 @default.
- W2102000945 cites W1979071892 @default.
- W2102000945 cites W1981627423 @default.
- W2102000945 cites W1992986973 @default.
- W2102000945 cites W1993711637 @default.
- W2102000945 cites W1995672065 @default.
- W2102000945 cites W2001729196 @default.
- W2102000945 cites W2009533501 @default.
- W2102000945 cites W2012036715 @default.
- W2102000945 cites W2016482167 @default.
- W2102000945 cites W2017103958 @default.
- W2102000945 cites W2020149918 @default.
- W2102000945 cites W2025240642 @default.
- W2102000945 cites W203646419 @default.
- W2102000945 cites W2043576939 @default.
- W2102000945 cites W2056354534 @default.
- W2102000945 cites W2060642394 @default.
- W2102000945 cites W2065356613 @default.
- W2102000945 cites W2084335986 @default.
- W2102000945 cites W2090985740 @default.
- W2102000945 cites W2097856935 @default.
- W2102000945 cites W2110538656 @default.
- W2102000945 cites W2114451917 @default.
- W2102000945 cites W2114562656 @default.
- W2102000945 cites W2117341272 @default.
- W2102000945 cites W2117757415 @default.
- W2102000945 cites W2121863487 @default.
- W2102000945 cites W2125132331 @default.
- W2102000945 cites W2129968755 @default.
- W2102000945 cites W2136851928 @default.
- W2102000945 cites W2137034368 @default.
- W2102000945 cites W2141234504 @default.
- W2102000945 cites W2146738023 @default.
- W2102000945 cites W2149276032 @default.
- W2102000945 cites W2149398074 @default.
- W2102000945 cites W2152166054 @default.
- W2102000945 cites W2153947321 @default.
- W2102000945 cites W2156067405 @default.
- W2102000945 cites W2156770822 @default.
- W2102000945 cites W2158548602 @default.
- W2102000945 cites W2160371091 @default.
- W2102000945 cites W2165131254 @default.
- W2102000945 cites W2168217230 @default.
- W2102000945 cites W2169022337 @default.
- W2102000945 cites W2291174979 @default.
- W2102000945 cites W2304844603 @default.
- W2102000945 cites W2343637401 @default.
- W2102000945 cites W2911432472 @default.
- W2102000945 cites W2912185451 @default.
- W2102000945 cites W2951774643 @default.
- W2102000945 cites W3028868262 @default.
- W2102000945 cites W73143588 @default.
- W2102000945 cites W89818670 @default.
- W2102000945 cites W2131600418 @default.
- W2102000945 hasPublicationYear "1998" @default.
- W2102000945 type Work @default.
- W2102000945 sameAs 2102000945 @default.
- W2102000945 citedByCount "59" @default.
- W2102000945 countsByYear W21020009452012 @default.
- W2102000945 countsByYear W21020009452016 @default.
- W2102000945 countsByYear W21020009452019 @default.
- W2102000945 countsByYear W21020009452020 @default.
- W2102000945 countsByYear W21020009452021 @default.
- W2102000945 crossrefType "journal-article" @default.
- W2102000945 hasAuthorship W2102000945A5004923102 @default.
- W2102000945 hasAuthorship W2102000945A5065366930 @default.
- W2102000945 hasAuthorship W2102000945A5065836447 @default.
- W2102000945 hasConcept C105795698 @default.
- W2102000945 hasConcept C106189395 @default.
- W2102000945 hasConcept C111472728 @default.