Matches in SemOpenAlex for { <https://semopenalex.org/work/W2037584050> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2037584050 endingPage "352" @default.
- W2037584050 startingPage "321" @default.
- W2037584050 abstract "An associative control process (ACP) network is a learning control system that can reproduce a variety of animal learning results from classical and instrumental conditioning experiments (Klopf, Morgan, & Weaver, 1993; see also the article, 'A Hierarchical Network of Control Systems that Learn). The ACP networks proposed and tested by Klopf, Morgan, and Weaver are not guaranteed, however, to learn optimal policies for maximizing reinforcement. Optimal behavior is guaranteed for a reinforcement learning system such as Q-learning (Watkins, 1989), but simple Q-learning is incapable of reproducing the animal learning results that ACP networks reproduce. We propose two new models that reproduce the animal learning results and are provably optimal. The first model, the modified ACP network, embodies the smallest number of changes necessary to the ACP network to guarantee that optimal policies will be learned while still reproducing the animal learning results. The second model, the single-layer ACP network, embodies the smallest number of changes necessary to Q-learning to guarantee that it reproduces the animal learning results while still learning optimal policies. We also propose a hierarchical network architecture within which several reinforcement learning systems (e.g., Q-learning systems, single-layer ACP networks, or any other learning controller) can be combined in a hierarchy. We implement the hierarchical network architecture by combining four of the single-layer ACP networks to form a controller for a standard inverted pendulum dynamic control problem. The hierarchical controller is shown to learn more reliably and more than an order of magnitude faster than either the single-layer ACP network or the Barto, Sutton, and Anderson (1983) learning controller for the benchmark problem." @default.
- W2037584050 created "2016-06-24" @default.
- W2037584050 creator A5038077029 @default.
- W2037584050 creator A5059725138 @default.
- W2037584050 date "1993-01-01" @default.
- W2037584050 modified "2023-09-25" @default.
- W2037584050 title "A Hierarchical Network of Provably Optimal Learning Control Systems: Extensions of the Associative Control Process (ACP) Network" @default.
- W2037584050 cites W2012036715 @default.
- W2037584050 cites W2012187514 @default.
- W2037584050 cites W2040598998 @default.
- W2037584050 cites W2064018461 @default.
- W2037584050 cites W2074935255 @default.
- W2037584050 cites W2080759927 @default.
- W2037584050 cites W2091565802 @default.
- W2037584050 cites W2097856935 @default.
- W2037584050 cites W2103626435 @default.
- W2037584050 cites W2141559645 @default.
- W2037584050 cites W2158091072 @default.
- W2037584050 cites W2161608691 @default.
- W2037584050 cites W3041202696 @default.
- W2037584050 cites W3198350258 @default.
- W2037584050 cites W32403112 @default.
- W2037584050 cites W4253365321 @default.
- W2037584050 doi "https://doi.org/10.1177/105971239300100303" @default.
- W2037584050 hasPublicationYear "1993" @default.
- W2037584050 type Work @default.
- W2037584050 sameAs 2037584050 @default.
- W2037584050 citedByCount "11" @default.
- W2037584050 crossrefType "journal-article" @default.
- W2037584050 hasAuthorship W2037584050A5038077029 @default.
- W2037584050 hasAuthorship W2037584050A5059725138 @default.
- W2037584050 hasConcept C111919701 @default.
- W2037584050 hasConcept C119857082 @default.
- W2037584050 hasConcept C124527596 @default.
- W2037584050 hasConcept C136197465 @default.
- W2037584050 hasConcept C154945302 @default.
- W2037584050 hasConcept C162324750 @default.
- W2037584050 hasConcept C188116033 @default.
- W2037584050 hasConcept C203479927 @default.
- W2037584050 hasConcept C2775924081 @default.
- W2037584050 hasConcept C31170391 @default.
- W2037584050 hasConcept C34447519 @default.
- W2037584050 hasConcept C41008148 @default.
- W2037584050 hasConcept C6557445 @default.
- W2037584050 hasConcept C86803240 @default.
- W2037584050 hasConcept C97541855 @default.
- W2037584050 hasConcept C98045186 @default.
- W2037584050 hasConceptScore W2037584050C111919701 @default.
- W2037584050 hasConceptScore W2037584050C119857082 @default.
- W2037584050 hasConceptScore W2037584050C124527596 @default.
- W2037584050 hasConceptScore W2037584050C136197465 @default.
- W2037584050 hasConceptScore W2037584050C154945302 @default.
- W2037584050 hasConceptScore W2037584050C162324750 @default.
- W2037584050 hasConceptScore W2037584050C188116033 @default.
- W2037584050 hasConceptScore W2037584050C203479927 @default.
- W2037584050 hasConceptScore W2037584050C2775924081 @default.
- W2037584050 hasConceptScore W2037584050C31170391 @default.
- W2037584050 hasConceptScore W2037584050C34447519 @default.
- W2037584050 hasConceptScore W2037584050C41008148 @default.
- W2037584050 hasConceptScore W2037584050C6557445 @default.
- W2037584050 hasConceptScore W2037584050C86803240 @default.
- W2037584050 hasConceptScore W2037584050C97541855 @default.
- W2037584050 hasConceptScore W2037584050C98045186 @default.
- W2037584050 hasIssue "3" @default.
- W2037584050 hasLocation W20375840501 @default.
- W2037584050 hasOpenAccess W2037584050 @default.
- W2037584050 hasPrimaryLocation W20375840501 @default.
- W2037584050 hasRelatedWork W1997001436 @default.
- W2037584050 hasRelatedWork W2084939417 @default.
- W2037584050 hasRelatedWork W2105611980 @default.
- W2037584050 hasRelatedWork W2154928376 @default.
- W2037584050 hasRelatedWork W2923653485 @default.
- W2037584050 hasRelatedWork W3022038857 @default.
- W2037584050 hasRelatedWork W4206669594 @default.
- W2037584050 hasRelatedWork W4220782901 @default.
- W2037584050 hasRelatedWork W4289712363 @default.
- W2037584050 hasRelatedWork W4319083788 @default.
- W2037584050 hasVolume "1" @default.
- W2037584050 isParatext "false" @default.
- W2037584050 isRetracted "false" @default.
- W2037584050 magId "2037584050" @default.
- W2037584050 workType "article" @default.