FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2755614540> ?p ?o ?g. }

• W2755614540 abstract "Deep Reinforcement Learning has been able to achieve amazing successes in a variety of domains from video games to continuous control by trying to maximize the cumulative reward. However, most of these successes rely on algorithms that require a large amount of data to train in order to obtain results on par with human-level performance. This is not feasible if we are to deploy these systems on real world tasks and hence there has been an increased thrust in exploring data efficient algorithms. To this end, we propose the Shared Learning framework aimed at making $Q$-ensemble algorithms data-efficient. For achieving this, we look into some principles of transfer learning which aim to study the benefits of information exchange across tasks in reinforcement learning and adapt transfer to learning our value function estimates in a novel manner. In this paper, we consider the special case of transfer between the value function estimates in the $Q$-ensemble architecture of BootstrappedDQN. We further empirically demonstrate how our proposed framework can help in speeding up the learning process in $Q$-ensembles with minimum computational overhead on a suite of Atari 2600 Games." @default.
• W2755614540 created "2017-09-25" @default.
• W2755614540 creator A5007638938 @default.
• W2755614540 creator A5009374923 @default.
• W2755614540 date "2017-09-14" @default.
• W2755614540 modified "2023-09-27" @default.
• W2755614540 title "Shared Learning : Enhancing Reinforcement in $Q$-Ensembles." @default.
• W2755614540 cites W1460713219 @default.
• W2755614540 cites W1505937442 @default.
• W2755614540 cites W1969685488 @default.
• W2755614540 cites W2097381042 @default.
• W2755614540 cites W2141559645 @default.
• W2755614540 cites W2145339207 @default.
• W2755614540 cites W2155968351 @default.
• W2755614540 cites W2168405694 @default.
• W2755614540 cites W2173564293 @default.
• W2755614540 cites W2201581102 @default.
• W2755614540 cites W2280163991 @default.
• W2755614540 cites W2417786368 @default.
• W2755614540 cites W2419612459 @default.
• W2755614540 cites W2584377191 @default.
• W2755614540 cites W2913317949 @default.
• W2755614540 cites W2919115771 @default.
• W2755614540 cites W2950872548 @default.
• W2755614540 cites W2962767126 @default.
• W2755614540 cites W2962858248 @default.
• W2755614540 cites W2963305465 @default.
• W2755614540 cites W2963946410 @default.
• W2755614540 cites W2964043796 @default.
• W2755614540 cites W3089091950 @default.
• W2755614540 hasPublicationYear "2017" @default.
• W2755614540 type Work @default.
• W2755614540 sameAs 2755614540 @default.
• W2755614540 citedByCount "0" @default.
• W2755614540 crossrefType "posted-content" @default.
• W2755614540 hasAuthorship W2755614540A5007638938 @default.
• W2755614540 hasAuthorship W2755614540A5009374923 @default.
• W2755614540 hasConcept C111919701 @default.
• W2755614540 hasConcept C119857082 @default.
• W2755614540 hasConcept C126255220 @default.
• W2755614540 hasConcept C136197465 @default.
• W2755614540 hasConcept C14036430 @default.
• W2755614540 hasConcept C14646407 @default.
• W2755614540 hasConcept C150899416 @default.
• W2755614540 hasConcept C154945302 @default.
• W2755614540 hasConcept C166957645 @default.
• W2755614540 hasConcept C188116033 @default.
• W2755614540 hasConcept C2779960059 @default.
• W2755614540 hasConcept C33923547 @default.
• W2755614540 hasConcept C41008148 @default.
• W2755614540 hasConcept C78458016 @default.
• W2755614540 hasConcept C79581498 @default.
• W2755614540 hasConcept C86803240 @default.
• W2755614540 hasConcept C95457728 @default.
• W2755614540 hasConcept C97541855 @default.
• W2755614540 hasConcept C98045186 @default.
• W2755614540 hasConceptScore W2755614540C111919701 @default.
• W2755614540 hasConceptScore W2755614540C119857082 @default.
• W2755614540 hasConceptScore W2755614540C126255220 @default.
• W2755614540 hasConceptScore W2755614540C136197465 @default.
• W2755614540 hasConceptScore W2755614540C14036430 @default.
• W2755614540 hasConceptScore W2755614540C14646407 @default.
• W2755614540 hasConceptScore W2755614540C150899416 @default.
• W2755614540 hasConceptScore W2755614540C154945302 @default.
• W2755614540 hasConceptScore W2755614540C166957645 @default.
• W2755614540 hasConceptScore W2755614540C188116033 @default.
• W2755614540 hasConceptScore W2755614540C2779960059 @default.
• W2755614540 hasConceptScore W2755614540C33923547 @default.
• W2755614540 hasConceptScore W2755614540C41008148 @default.
• W2755614540 hasConceptScore W2755614540C78458016 @default.
• W2755614540 hasConceptScore W2755614540C79581498 @default.
• W2755614540 hasConceptScore W2755614540C86803240 @default.
• W2755614540 hasConceptScore W2755614540C95457728 @default.
• W2755614540 hasConceptScore W2755614540C97541855 @default.
• W2755614540 hasConceptScore W2755614540C98045186 @default.
• W2755614540 hasLocation W27556145401 @default.
• W2755614540 hasOpenAccess W2755614540 @default.
• W2755614540 hasPrimaryLocation W27556145401 @default.
• W2755614540 hasRelatedWork W2111770102 @default.
• W2755614540 hasRelatedWork W2128786740 @default.
• W2755614540 hasRelatedWork W2199825521 @default.
• W2755614540 hasRelatedWork W2253140532 @default.
• W2755614540 hasRelatedWork W2294805292 @default.
• W2755614540 hasRelatedWork W2549891446 @default.
• W2755614540 hasRelatedWork W2593766708 @default.
• W2755614540 hasRelatedWork W2626860042 @default.
• W2755614540 hasRelatedWork W2905301513 @default.
• W2755614540 hasRelatedWork W2946232168 @default.
• W2755614540 hasRelatedWork W2948199691 @default.
• W2755614540 hasRelatedWork W2950602341 @default.
• W2755614540 hasRelatedWork W2963846183 @default.
• W2755614540 hasRelatedWork W2980297462 @default.
• W2755614540 hasRelatedWork W2995102855 @default.
• W2755614540 hasRelatedWork W3006231530 @default.
• W2755614540 hasRelatedWork W3030598573 @default.
• W2755614540 hasRelatedWork W3084024636 @default.
• W2755614540 hasRelatedWork W3151079898 @default.
• W2755614540 hasRelatedWork W3095548673 @default.
• W2755614540 isParatext "false" @default.
• W2755614540 isRetracted "false" @default.

• next