Matches in SemOpenAlex for { <https://semopenalex.org/work/W2022795107> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2022795107 endingPage "120" @default.
- W2022795107 startingPage "112" @default.
- W2022795107 abstract "Reinforcement learning is one of the more prominent machine learning technologies , because of its unsupervised learning structure and its ability to produce continual learning, even in a dynamic operating environment. Applying this learning to cooperative multi-agent systems not only allows each individual agent to learn from its own experience, but also offers the opportunity for the individual agents to learn from other agents in the system, in order to increase the speed of learning. In the proposed learning algorithm, an agent stores its experience in terms of a state aggregation, by use of a decision tree, such that policy sharing between multiple agents is eventually accomplished by merging the different decision trees of peers. Unlike lookup tables , which have a homogeneous structure for state aggregation, decision trees carried with in agents have a heterogeneous structure. The method detailed in this study allows policy sharing between cooperative agents by means merging their trees into a hyper-structure, instead of forcefully merging entire trees. The proposed scheme initially allows the entire decision tree to be translated from one agent to others. Based on the evidence, only partial leaf nodes have useful experience for use in policy sharing. The proposed method induces a hyper decision tree by using a large amount of samples that are sampled from the shared nodes. The results from simulations in a multi-agent cooperative domain illustrate that the proposed algorithms perform better than the algorithm that does not allow sharing." @default.
- W2022795107 created "2016-06-24" @default.
- W2022795107 creator A5061189209 @default.
- W2022795107 creator A5064655192 @default.
- W2022795107 date "2013-06-01" @default.
- W2022795107 modified "2023-09-24" @default.
- W2022795107 title "Policy sharing between multiple mobile robots using decision trees" @default.
- W2022795107 cites W1492518272 @default.
- W2022795107 cites W1515851193 @default.
- W2022795107 cites W1783866091 @default.
- W2022795107 cites W1994875077 @default.
- W2022795107 cites W2003171415 @default.
- W2022795107 cites W2024130228 @default.
- W2022795107 cites W2024848225 @default.
- W2022795107 cites W2041872606 @default.
- W2022795107 cites W2046727971 @default.
- W2022795107 cites W2072655801 @default.
- W2022795107 cites W2078196735 @default.
- W2022795107 cites W2095487261 @default.
- W2022795107 cites W2115471292 @default.
- W2022795107 cites W2116430682 @default.
- W2022795107 cites W2119525113 @default.
- W2022795107 cites W2121863487 @default.
- W2022795107 cites W2124476435 @default.
- W2022795107 cites W2125055259 @default.
- W2022795107 cites W2137564278 @default.
- W2022795107 cites W2141056154 @default.
- W2022795107 cites W2146871603 @default.
- W2022795107 cites W2147319420 @default.
- W2022795107 cites W2147492008 @default.
- W2022795107 cites W3085162807 @default.
- W2022795107 doi "https://doi.org/10.1016/j.ins.2013.01.008" @default.
- W2022795107 hasPublicationYear "2013" @default.
- W2022795107 type Work @default.
- W2022795107 sameAs 2022795107 @default.
- W2022795107 citedByCount "9" @default.
- W2022795107 countsByYear W20227951072013 @default.
- W2022795107 countsByYear W20227951072014 @default.
- W2022795107 countsByYear W20227951072015 @default.
- W2022795107 countsByYear W20227951072017 @default.
- W2022795107 countsByYear W20227951072018 @default.
- W2022795107 countsByYear W20227951072019 @default.
- W2022795107 countsByYear W20227951072020 @default.
- W2022795107 crossrefType "journal-article" @default.
- W2022795107 hasAuthorship W2022795107A5061189209 @default.
- W2022795107 hasAuthorship W2022795107A5064655192 @default.
- W2022795107 hasConcept C10229987 @default.
- W2022795107 hasConcept C113174947 @default.
- W2022795107 hasConcept C11413529 @default.
- W2022795107 hasConcept C119857082 @default.
- W2022795107 hasConcept C120314980 @default.
- W2022795107 hasConcept C134306372 @default.
- W2022795107 hasConcept C154945302 @default.
- W2022795107 hasConcept C163797641 @default.
- W2022795107 hasConcept C197855036 @default.
- W2022795107 hasConcept C33923547 @default.
- W2022795107 hasConcept C36503486 @default.
- W2022795107 hasConcept C41008148 @default.
- W2022795107 hasConcept C5481197 @default.
- W2022795107 hasConcept C84525736 @default.
- W2022795107 hasConcept C97541855 @default.
- W2022795107 hasConceptScore W2022795107C10229987 @default.
- W2022795107 hasConceptScore W2022795107C113174947 @default.
- W2022795107 hasConceptScore W2022795107C11413529 @default.
- W2022795107 hasConceptScore W2022795107C119857082 @default.
- W2022795107 hasConceptScore W2022795107C120314980 @default.
- W2022795107 hasConceptScore W2022795107C134306372 @default.
- W2022795107 hasConceptScore W2022795107C154945302 @default.
- W2022795107 hasConceptScore W2022795107C163797641 @default.
- W2022795107 hasConceptScore W2022795107C197855036 @default.
- W2022795107 hasConceptScore W2022795107C33923547 @default.
- W2022795107 hasConceptScore W2022795107C36503486 @default.
- W2022795107 hasConceptScore W2022795107C41008148 @default.
- W2022795107 hasConceptScore W2022795107C5481197 @default.
- W2022795107 hasConceptScore W2022795107C84525736 @default.
- W2022795107 hasConceptScore W2022795107C97541855 @default.
- W2022795107 hasLocation W20227951071 @default.
- W2022795107 hasOpenAccess W2022795107 @default.
- W2022795107 hasPrimaryLocation W20227951071 @default.
- W2022795107 hasRelatedWork W1485652503 @default.
- W2022795107 hasRelatedWork W2033139852 @default.
- W2022795107 hasRelatedWork W2068624253 @default.
- W2022795107 hasRelatedWork W2738041616 @default.
- W2022795107 hasRelatedWork W2954804306 @default.
- W2022795107 hasRelatedWork W3094337650 @default.
- W2022795107 hasRelatedWork W3202663598 @default.
- W2022795107 hasRelatedWork W4225905846 @default.
- W2022795107 hasRelatedWork W4288289200 @default.
- W2022795107 hasRelatedWork W936909164 @default.
- W2022795107 hasVolume "234" @default.
- W2022795107 isParatext "false" @default.
- W2022795107 isRetracted "false" @default.
- W2022795107 magId "2022795107" @default.
- W2022795107 workType "article" @default.