FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2904339729> ?p ?o ?g. }

• W2904339729 abstract "The ability of a reinforcement learning (RL) agent to learn about many reward functions at the same time has many potential benefits, such as the decomposition of complex tasks into simpler ones, the exchange of information between tasks, and the reuse of skills. We focus on one aspect in particular, namely the ability to generalise to unseen tasks. Parametric generalisation relies on the interpolation power of a function approximator that is given the task description as input; one of its most common form are universal value function approximators (UVFAs). Another way to generalise to new tasks is to exploit structure in the RL problem itself. Generalised policy improvement (GPI) combines solutions of previous tasks into a policy for the unseen task; this relies on instantaneous policy evaluation of old policies under the new reward function, which is made possible through successor features (SFs). Our proposed universal successor features approximators (USFAs) combine the advantages of all of these, namely the scalability of UVFAs, the instant inference of SFs, and the strong generalisation of GPI. We discuss the challenges involved in training a USFA, its generalisation properties and demonstrate its practical benefits and transfer abilities on a large-scale domain in which the agent has to navigate in a first-person perspective three-dimensional environment." @default.
• W2904339729 created "2018-12-22" @default.
• W2904339729 creator A5006533777 @default.
• W2904339729 creator A5008592589 @default.
• W2904339729 creator A5018191427 @default.
• W2904339729 creator A5033135596 @default.
• W2904339729 creator A5071714901 @default.
• W2904339729 creator A5079599342 @default.
• W2904339729 creator A5081322018 @default.
• W2904339729 creator A5091771290 @default.
• W2904339729 date "2018-12-18" @default.
• W2904339729 modified "2023-09-27" @default.
• W2904339729 title "Universal Successor Features Approximators." @default.
• W2904339729 cites W158722652 @default.
• W2904339729 cites W1594201624 @default.
• W2904339729 cites W2073384958 @default.
• W2904339729 cites W2097381042 @default.
• W2904339729 cites W2119567691 @default.
• W2904339729 cites W2121863487 @default.
• W2904339729 cites W2145339207 @default.
• W2904339729 cites W2417089653 @default.
• W2904339729 cites W2534060593 @default.
• W2904339729 cites W2560647685 @default.
• W2904339729 cites W2567020712 @default.
• W2904339729 cites W2627585944 @default.
• W2904339729 cites W2733961795 @default.
• W2904339729 cites W2735995851 @default.
• W2904339729 cites W2786036274 @default.
• W2904339729 cites W2788146012 @default.
• W2904339729 cites W2797734773 @default.
• W2904339729 cites W2804673281 @default.
• W2904339729 cites W2949267040 @default.
• W2904339729 cites W2950202163 @default.
• W2904339729 cites W2953326374 @default.
• W2904339729 cites W2962717849 @default.
• W2904339729 cites W2964262254 @default.
• W2904339729 cites W3011120880 @default.
• W2904339729 cites W567721252 @default.
• W2904339729 cites W2426267443 @default.
• W2904339729 hasPublicationYear "2018" @default.
• W2904339729 type Work @default.
• W2904339729 sameAs 2904339729 @default.
• W2904339729 citedByCount "18" @default.
• W2904339729 countsByYear W29043397292019 @default.
• W2904339729 countsByYear W29043397292020 @default.
• W2904339729 countsByYear W29043397292021 @default.
• W2904339729 crossrefType "posted-content" @default.
• W2904339729 hasAuthorship W2904339729A5006533777 @default.
• W2904339729 hasAuthorship W2904339729A5008592589 @default.
• W2904339729 hasAuthorship W2904339729A5018191427 @default.
• W2904339729 hasAuthorship W2904339729A5033135596 @default.
• W2904339729 hasAuthorship W2904339729A5071714901 @default.
• W2904339729 hasAuthorship W2904339729A5079599342 @default.
• W2904339729 hasAuthorship W2904339729A5081322018 @default.
• W2904339729 hasAuthorship W2904339729A5091771290 @default.
• W2904339729 hasConcept C119857082 @default.
• W2904339729 hasConcept C134306372 @default.
• W2904339729 hasConcept C14036430 @default.
• W2904339729 hasConcept C154945302 @default.
• W2904339729 hasConcept C162324750 @default.
• W2904339729 hasConcept C165696696 @default.
• W2904339729 hasConcept C187736073 @default.
• W2904339729 hasConcept C2776214188 @default.
• W2904339729 hasConcept C2780451532 @default.
• W2904339729 hasConcept C33923547 @default.
• W2904339729 hasConcept C36503486 @default.
• W2904339729 hasConcept C38652104 @default.
• W2904339729 hasConcept C41008148 @default.
• W2904339729 hasConcept C48044578 @default.
• W2904339729 hasConcept C75306776 @default.
• W2904339729 hasConcept C77088390 @default.
• W2904339729 hasConcept C78458016 @default.
• W2904339729 hasConcept C86803240 @default.
• W2904339729 hasConcept C97541855 @default.
• W2904339729 hasConceptScore W2904339729C119857082 @default.
• W2904339729 hasConceptScore W2904339729C134306372 @default.
• W2904339729 hasConceptScore W2904339729C14036430 @default.
• W2904339729 hasConceptScore W2904339729C154945302 @default.
• W2904339729 hasConceptScore W2904339729C162324750 @default.
• W2904339729 hasConceptScore W2904339729C165696696 @default.
• W2904339729 hasConceptScore W2904339729C187736073 @default.
• W2904339729 hasConceptScore W2904339729C2776214188 @default.
• W2904339729 hasConceptScore W2904339729C2780451532 @default.
• W2904339729 hasConceptScore W2904339729C33923547 @default.
• W2904339729 hasConceptScore W2904339729C36503486 @default.
• W2904339729 hasConceptScore W2904339729C38652104 @default.
• W2904339729 hasConceptScore W2904339729C41008148 @default.
• W2904339729 hasConceptScore W2904339729C48044578 @default.
• W2904339729 hasConceptScore W2904339729C75306776 @default.
• W2904339729 hasConceptScore W2904339729C77088390 @default.
• W2904339729 hasConceptScore W2904339729C78458016 @default.
• W2904339729 hasConceptScore W2904339729C86803240 @default.
• W2904339729 hasConceptScore W2904339729C97541855 @default.
• W2904339729 hasLocation W29043397291 @default.
• W2904339729 hasOpenAccess W2904339729 @default.
• W2904339729 hasPrimaryLocation W29043397291 @default.
• W2904339729 hasRelatedWork W158722652 @default.
• W2904339729 hasRelatedWork W2056354534 @default.
• W2904339729 hasRelatedWork W2097381042 @default.
• W2904339729 hasRelatedWork W2121863487 @default.

• next