FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1870357915> ?p ?o ?g. }

• W1870357915 abstract "This paper presents a model allowing to tune continual exploration in an optimal way by integrating exploration and exploitation in a common framework. It first quantifies exploration by defining the degree of exploration of a state as the entropy of the probability distribution for choosing an admissible action. Then, the exploration/exploitation tradeoff is formulated as a global optimization problem: find the exploration strategy that minimizes the expected cumulated cost, while maintaining fixed degrees of exploration at the states. In other words, exploitation is maximized for constant exploration. This formulation leads to a set of nonlinear iterative equations reminiscent of the value-iteration algorithm. Their convergence to a local minimum can be proved for a stationary environment. Interestingly, in the deterministic case, when there is no exploration, these equations reduce to the Bellman equations for finding the shortest path. If the graph of states is directed and acyclic, the nonlinear equations can easily be solved by a single backward pass from the destination state. Stochastic shortest-path problems and discounted problems are also examined, and they are compared to the SARSA algorithm. The theoretical results are confirmed by simple simulations showing that the proposed exploration strategy outperforms the ǫ-greedy and the naive Boltzmann strategies." @default.
• W1870357915 created "2016-06-24" @default.
• W1870357915 creator A5003064169 @default.
• W1870357915 creator A5015460788 @default.
• W1870357915 creator A5025189765 @default.
• W1870357915 creator A5050531481 @default.
• W1870357915 creator A5087174204 @default.
• W1870357915 date "2007-01-01" @default.
• W1870357915 modified "2023-09-27" @default.
• W1870357915 title "Tuning Continual Exploration in Reinforcement Learning" @default.
• W1870357915 cites W105074360 @default.
• W1870357915 cites W1497576442 @default.
• W1870357915 cites W1504212531 @default.
• W1870357915 cites W1535491338 @default.
• W1870357915 cites W1559582792 @default.
• W1870357915 cites W1576452626 @default.
• W1870357915 cites W1597966850 @default.
• W1870357915 cites W1689629105 @default.
• W1870357915 cites W1781665229 @default.
• W1870357915 cites W2001560396 @default.
• W1870357915 cites W2003274998 @default.
• W1870357915 cites W203276351 @default.
• W1870357915 cites W2075379212 @default.
• W1870357915 cites W2098432798 @default.
• W1870357915 cites W2113913482 @default.
• W1870357915 cites W2121863487 @default.
• W1870357915 cites W2156666755 @default.
• W1870357915 cites W2161984370 @default.
• W1870357915 cites W2279353332 @default.
• W1870357915 cites W2336416123 @default.
• W1870357915 cites W2787523326 @default.
• W1870357915 cites W2911640577 @default.
• W1870357915 cites W3011120880 @default.
• W1870357915 cites W3139377883 @default.
• W1870357915 cites W65193931 @default.
• W1870357915 hasPublicationYear "2007" @default.
• W1870357915 type Work @default.
• W1870357915 sameAs 1870357915 @default.
• W1870357915 citedByCount "1" @default.
• W1870357915 crossrefType "journal-article" @default.
• W1870357915 hasAuthorship W1870357915A5003064169 @default.
• W1870357915 hasAuthorship W1870357915A5015460788 @default.
• W1870357915 hasAuthorship W1870357915A5025189765 @default.
• W1870357915 hasAuthorship W1870357915A5050531481 @default.
• W1870357915 hasAuthorship W1870357915A5087174204 @default.
• W1870357915 hasConcept C11413529 @default.
• W1870357915 hasConcept C121332964 @default.
• W1870357915 hasConcept C126255220 @default.
• W1870357915 hasConcept C132525143 @default.
• W1870357915 hasConcept C146380142 @default.
• W1870357915 hasConcept C154945302 @default.
• W1870357915 hasConcept C158622935 @default.
• W1870357915 hasConcept C162324750 @default.
• W1870357915 hasConcept C199360897 @default.
• W1870357915 hasConcept C22590252 @default.
• W1870357915 hasConcept C2777303404 @default.
• W1870357915 hasConcept C2777735758 @default.
• W1870357915 hasConcept C33923547 @default.
• W1870357915 hasConcept C41008148 @default.
• W1870357915 hasConcept C50522688 @default.
• W1870357915 hasConcept C62520636 @default.
• W1870357915 hasConcept C80444323 @default.
• W1870357915 hasConcept C97541855 @default.
• W1870357915 hasConceptScore W1870357915C11413529 @default.
• W1870357915 hasConceptScore W1870357915C121332964 @default.
• W1870357915 hasConceptScore W1870357915C126255220 @default.
• W1870357915 hasConceptScore W1870357915C132525143 @default.
• W1870357915 hasConceptScore W1870357915C146380142 @default.
• W1870357915 hasConceptScore W1870357915C154945302 @default.
• W1870357915 hasConceptScore W1870357915C158622935 @default.
• W1870357915 hasConceptScore W1870357915C162324750 @default.
• W1870357915 hasConceptScore W1870357915C199360897 @default.
• W1870357915 hasConceptScore W1870357915C22590252 @default.
• W1870357915 hasConceptScore W1870357915C2777303404 @default.
• W1870357915 hasConceptScore W1870357915C2777735758 @default.
• W1870357915 hasConceptScore W1870357915C33923547 @default.
• W1870357915 hasConceptScore W1870357915C41008148 @default.
• W1870357915 hasConceptScore W1870357915C50522688 @default.
• W1870357915 hasConceptScore W1870357915C62520636 @default.
• W1870357915 hasConceptScore W1870357915C80444323 @default.
• W1870357915 hasConceptScore W1870357915C97541855 @default.
• W1870357915 hasLocation W18703579151 @default.
• W1870357915 hasOpenAccess W1870357915 @default.
• W1870357915 hasPrimaryLocation W18703579151 @default.
• W1870357915 hasRelatedWork W1710134642 @default.
• W1870357915 hasRelatedWork W1990453721 @default.
• W1870357915 hasRelatedWork W202180931 @default.
• W1870357915 hasRelatedWork W2042708996 @default.
• W1870357915 hasRelatedWork W2092203504 @default.
• W1870357915 hasRelatedWork W2098432798 @default.
• W1870357915 hasRelatedWork W2101365705 @default.
• W1870357915 hasRelatedWork W2104753538 @default.
• W1870357915 hasRelatedWork W2141814822 @default.
• W1870357915 hasRelatedWork W2142383762 @default.
• W1870357915 hasRelatedWork W2148864095 @default.
• W1870357915 hasRelatedWork W2279353332 @default.
• W1870357915 hasRelatedWork W2359964334 @default.
• W1870357915 hasRelatedWork W2373808749 @default.
• W1870357915 hasRelatedWork W2547703543 @default.
• W1870357915 hasRelatedWork W2813777834 @default.

• next