Matches in SemOpenAlex for { <https://semopenalex.org/work/W67929074> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W67929074 abstract "This document describes an approach to reinforcement learning, called situational reinforcement learning (SRL). The main goal of the approach is to reduce the computational cost of learning behaviour in comparison to conventional reinforcement learning. One of the main goals of the research described in this document is to evaluate the implication of situational reinforcement learning on the computational cost of learning behaviour and on the optimality of the learned behaviour. The reduction in computational cost is mainly facilitated by decomposing the environment into smaller environments ? called situations ? and only learn behaviour ? called a policy ? for each situation. A global policy is then created bycombining all learned situational policies. Each situation is based upon states that have an equal heuristic preference value. The learned behaviour of a situation will most likely direct the agent to a reachable, more favourable situation. The global policy that is created from combining the situational policies will therefore focus on continually reaching more favourable situations. The research not only evaluates the use of situational reinforcement learning as a stand-alone approach to artificial intelligence (AI) learning, but also applies the approach as an addition to conventional reinforcement learning. The method that uses SRL as a stand-alone approach will be referenced to as the Combined method and the method that uses it as an addition to conventional methods will be referenced to as the Enhanced method. Evaluation of the Combined method shows that the method achieves significant computational cost reductions. Unfortunately, this reduction does not come without a price and the evaluation shows that careful consideration of the heuristic function is required in order to reduce the optimality loss. The evaluation of the Enhanced method shows that oneverage, when using the modified policy iteration algorithm to learn policies, the computational cost of learning a global policy is greater than when the conventional method is solely used. I believe that the significant reduction in computational cost resulting from the use of SRL is a good incentive to perform further research on this approach." @default.
- W67929074 created "2016-06-24" @default.
- W67929074 creator A5076227976 @default.
- W67929074 date "2006-01-01" @default.
- W67929074 modified "2023-09-27" @default.
- W67929074 title "Situational reinforcement learning : learning and combining local policies by using heuristic state preference values" @default.
- W67929074 hasPublicationYear "2006" @default.
- W67929074 type Work @default.
- W67929074 sameAs 67929074 @default.
- W67929074 citedByCount "0" @default.
- W67929074 crossrefType "dissertation" @default.
- W67929074 hasAuthorship W67929074A5076227976 @default.
- W67929074 hasConcept C105795698 @default.
- W67929074 hasConcept C111335779 @default.
- W67929074 hasConcept C119857082 @default.
- W67929074 hasConcept C154945302 @default.
- W67929074 hasConcept C15744967 @default.
- W67929074 hasConcept C173801870 @default.
- W67929074 hasConcept C188116033 @default.
- W67929074 hasConcept C2524010 @default.
- W67929074 hasConcept C2781249084 @default.
- W67929074 hasConcept C33923547 @default.
- W67929074 hasConcept C41008148 @default.
- W67929074 hasConcept C67203356 @default.
- W67929074 hasConcept C77805123 @default.
- W67929074 hasConcept C9114305 @default.
- W67929074 hasConcept C97541855 @default.
- W67929074 hasConceptScore W67929074C105795698 @default.
- W67929074 hasConceptScore W67929074C111335779 @default.
- W67929074 hasConceptScore W67929074C119857082 @default.
- W67929074 hasConceptScore W67929074C154945302 @default.
- W67929074 hasConceptScore W67929074C15744967 @default.
- W67929074 hasConceptScore W67929074C173801870 @default.
- W67929074 hasConceptScore W67929074C188116033 @default.
- W67929074 hasConceptScore W67929074C2524010 @default.
- W67929074 hasConceptScore W67929074C2781249084 @default.
- W67929074 hasConceptScore W67929074C33923547 @default.
- W67929074 hasConceptScore W67929074C41008148 @default.
- W67929074 hasConceptScore W67929074C67203356 @default.
- W67929074 hasConceptScore W67929074C77805123 @default.
- W67929074 hasConceptScore W67929074C9114305 @default.
- W67929074 hasConceptScore W67929074C97541855 @default.
- W67929074 hasLocation W679290741 @default.
- W67929074 hasOpenAccess W67929074 @default.
- W67929074 hasPrimaryLocation W679290741 @default.
- W67929074 hasRelatedWork W116417374 @default.
- W67929074 hasRelatedWork W120804890 @default.
- W67929074 hasRelatedWork W1576253121 @default.
- W67929074 hasRelatedWork W1586172133 @default.
- W67929074 hasRelatedWork W1786568574 @default.
- W67929074 hasRelatedWork W1998314229 @default.
- W67929074 hasRelatedWork W2129297552 @default.
- W67929074 hasRelatedWork W2154023516 @default.
- W67929074 hasRelatedWork W2475178090 @default.
- W67929074 hasRelatedWork W2857779301 @default.
- W67929074 hasRelatedWork W2910911697 @default.
- W67929074 hasRelatedWork W2954804306 @default.
- W67929074 hasRelatedWork W2963065769 @default.
- W67929074 hasRelatedWork W2978084855 @default.
- W67929074 hasRelatedWork W2997735228 @default.
- W67929074 hasRelatedWork W2997876358 @default.
- W67929074 hasRelatedWork W3072315125 @default.
- W67929074 hasRelatedWork W3105659172 @default.
- W67929074 hasRelatedWork W3122329924 @default.
- W67929074 hasRelatedWork W3148270135 @default.
- W67929074 isParatext "false" @default.
- W67929074 isRetracted "false" @default.
- W67929074 magId "67929074" @default.
- W67929074 workType "dissertation" @default.