FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2111967991> ?p ?o ?g. }

• W2111967991 abstract "Many reinforcement learning (RL) tasks, especially in robotics, consist of multiple sub-tasks that are strongly structured. Such task structures can be exploited by incorporating hierarchical policies that consist of gating networks and sub-policies. However, this concept has only been partially explored for real world settings and complete methods, derived from first principles, are needed. Real world settings are challenging due to large and continuous state-action spaces that are prohibitive for exhaustive sampling methods. We define the problem of learning sub-policies in continuous state action spaces as finding a hierarchical policy that is composed of a high-level gating policy to select the low-level sub-policies for execution by the agent. In order to efficiently share experience with all sub-policies, also called inter-policy learning, we treat these sub-policies as latent variables which allows for distribution of the update information between the sub-policies. We present three different variants of our algorithm, designed to be suitable for a wide variety of real world robot learning tasks and evaluate our algorithms in two real robot learning scenarios as well as several simulations and comparisons." @default.
• W2111967991 created "2016-06-24" @default.
• W2111967991 creator A5005091065 @default.
• W2111967991 creator A5047982234 @default.
• W2111967991 creator A5071367253 @default.
• W2111967991 creator A5088394978 @default.
• W2111967991 date "2014-01-04" @default.
• W2111967991 modified "2023-10-02" @default.
• W2111967991 title "Hierarchical Relative Entropy Policy Search" @default.
• W2111967991 cites W1486707268 @default.
• W2111967991 cites W1494114146 @default.
• W2111967991 cites W1499669280 @default.
• W2111967991 cites W1515851193 @default.
• W2111967991 cites W1528215793 @default.
• W2111967991 cites W1564755532 @default.
• W2111967991 cites W1592847719 @default.
• W2111967991 cites W1685912164 @default.
• W2111967991 cites W1771410628 @default.
• W2111967991 cites W181022050 @default.
• W2111967991 cites W1925816294 @default.
• W2111967991 cites W1929309940 @default.
• W2111967991 cites W1952489873 @default.
• W2111967991 cites W1973102501 @default.
• W2111967991 cites W1982803779 @default.
• W2111967991 cites W2012204020 @default.
• W2111967991 cites W2012392077 @default.
• W2111967991 cites W2016765487 @default.
• W2111967991 cites W2017611213 @default.
• W2111967991 cites W2020920737 @default.
• W2111967991 cites W2049633694 @default.
• W2111967991 cites W2051620263 @default.
• W2111967991 cites W2054681192 @default.
• W2111967991 cites W2063591749 @default.
• W2111967991 cites W2071444114 @default.
• W2111967991 cites W2080039641 @default.
• W2111967991 cites W2088038240 @default.
• W2111967991 cites W2097828232 @default.
• W2111967991 cites W2106261932 @default.
• W2111967991 cites W2108535023 @default.
• W2111967991 cites W2108579172 @default.
• W2111967991 cites W2109910161 @default.
• W2111967991 cites W2114537044 @default.
• W2111967991 cites W2116226448 @default.
• W2111967991 cites W2121103318 @default.
• W2111967991 cites W2121517924 @default.
• W2111967991 cites W2121863487 @default.
• W2111967991 cites W2123967136 @default.
• W2111967991 cites W2124175081 @default.
• W2111967991 cites W2126049034 @default.
• W2111967991 cites W2126685977 @default.
• W2111967991 cites W2127107099 @default.
• W2111967991 cites W2130105540 @default.
• W2111967991 cites W2138537392 @default.
• W2111967991 cites W2139053308 @default.
• W2111967991 cites W2139394304 @default.
• W2111967991 cites W2140135625 @default.
• W2111967991 cites W2143072483 @default.
• W2111967991 cites W2149860990 @default.
• W2111967991 cites W2151965738 @default.
• W2111967991 cites W2155027007 @default.
• W2111967991 cites W2155791599 @default.
• W2111967991 cites W2167647761 @default.
• W2111967991 cites W2168820925 @default.
• W2111967991 cites W2179284380 @default.
• W2111967991 cites W2211399972 @default.
• W2111967991 cites W2245825236 @default.
• W2111967991 cites W2951458352 @default.
• W2111967991 cites W2962901215 @default.
• W2111967991 cites W314779054 @default.
• W2111967991 hasPublicationYear "2014" @default.
• W2111967991 type Work @default.
• W2111967991 sameAs 2111967991 @default.
• W2111967991 citedByCount "93" @default.
• W2111967991 countsByYear W21119679912012 @default.
• W2111967991 countsByYear W21119679912013 @default.
• W2111967991 countsByYear W21119679912014 @default.
• W2111967991 countsByYear W21119679912015 @default.
• W2111967991 countsByYear W21119679912016 @default.
• W2111967991 countsByYear W21119679912017 @default.
• W2111967991 countsByYear W21119679912018 @default.
• W2111967991 countsByYear W21119679912019 @default.
• W2111967991 countsByYear W21119679912020 @default.
• W2111967991 countsByYear W21119679912021 @default.
• W2111967991 countsByYear W21119679912022 @default.
• W2111967991 countsByYear W21119679912023 @default.
• W2111967991 crossrefType "book" @default.
• W2111967991 hasAuthorship W2111967991A5005091065 @default.
• W2111967991 hasAuthorship W2111967991A5047982234 @default.
• W2111967991 hasAuthorship W2111967991A5071367253 @default.
• W2111967991 hasAuthorship W2111967991A5088394978 @default.
• W2111967991 hasConcept C106301342 @default.
• W2111967991 hasConcept C119857082 @default.
• W2111967991 hasConcept C121332964 @default.
• W2111967991 hasConcept C127413603 @default.
• W2111967991 hasConcept C136197465 @default.
• W2111967991 hasConcept C154945302 @default.
• W2111967991 hasConcept C201995342 @default.
• W2111967991 hasConcept C2780451532 @default.
• W2111967991 hasConcept C34413123 @default.
• W2111967991 hasConcept C41008148 @default.

• next