FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2922388521> ?p ?o ?g. }

• W2922388521 abstract "Exploration in sparse reward reinforcement learning remains an open challenge. Many state-of-the-art methods use intrinsic motivation to complement the sparse extrinsic reward signal, giving the agent more opportunities to receive feedback during exploration. Commonly these signals are added as bonus rewards, which results in a mixture policy that neither conducts exploration nor task fulfillment resolutely. In this paper, we instead learn separate intrinsic and extrinsic task policies and schedule between these different drives to accelerate exploration and stabilize learning. Moreover, we introduce a new type of intrinsic reward denoted as successor feature control (SFC), which is general and not task-specific. It takes into account statistics over complete trajectories and thus differs from previous methods that only use local information to evaluate intrinsic motivation. We evaluate our proposed scheduled intrinsic drive (SID) agent using three different environments with pure visual inputs: VizDoom, DeepMind Lab and DeepMind Control Suite. The results show a substantially improved exploration efficiency with SFC and the hierarchical usage of the intrinsic drives. A video of our experimental results can be found at https://youtu.be/b0MbY3lUlEI." @default.
• W2922388521 created "2019-03-22" @default.
• W2922388521 creator A5036340517 @default.
• W2922388521 creator A5038908529 @default.
• W2922388521 creator A5055864987 @default.
• W2922388521 creator A5071878141 @default.
• W2922388521 creator A5084499878 @default.
• W2922388521 date "2019-03-18" @default.
• W2922388521 modified "2023-09-26" @default.
• W2922388521 title "Scheduled Intrinsic Drive: A Hierarchical Take on Intrinsically Motivated Exploration" @default.
• W2922388521 cites W1480053368 @default.
• W2922388521 cites W1522301498 @default.
• W2922388521 cites W2034806191 @default.
• W2922388521 cites W2056354534 @default.
• W2922388521 cites W2109910161 @default.
• W2922388521 cites W2121863487 @default.
• W2922388521 cites W2145339207 @default.
• W2922388521 cites W2163176541 @default.
• W2922388521 cites W2247242831 @default.
• W2922388521 cites W2417089653 @default.
• W2922388521 cites W2596982695 @default.
• W2922388521 cites W2736601468 @default.
• W2922388521 cites W2751973545 @default.
• W2922388521 cites W2765308067 @default.
• W2922388521 cites W2781585732 @default.
• W2922388521 cites W2786036274 @default.
• W2922388521 cites W2786928559 @default.
• W2922388521 cites W2788953735 @default.
• W2922388521 cites W2885550588 @default.
• W2922388521 cites W2895453875 @default.
• W2922388521 cites W2899205164 @default.
• W2922388521 cites W2899771611 @default.
• W2922388521 cites W2949117887 @default.
• W2922388521 cites W2949267040 @default.
• W2922388521 cites W2950872548 @default.
• W2922388521 cites W2952791429 @default.
• W2922388521 cites W2962717849 @default.
• W2922388521 cites W2963019567 @default.
• W2922388521 cites W2963262099 @default.
• W2922388521 cites W2963276097 @default.
• W2922388521 cites W2963761387 @default.
• W2922388521 cites W2963871073 @default.
• W2922388521 cites W2964043796 @default.
• W2922388521 cites W2964118020 @default.
• W2922388521 cites W2964227312 @default.
• W2922388521 cites W2964311356 @default.
• W2922388521 cites W2997289589 @default.
• W2922388521 doi "https://doi.org/10.48550/arxiv.1903.07400" @default.
• W2922388521 hasPublicationYear "2019" @default.
• W2922388521 type Work @default.
• W2922388521 sameAs 2922388521 @default.
• W2922388521 citedByCount "13" @default.
• W2922388521 countsByYear W29223885212019 @default.
• W2922388521 countsByYear W29223885212020 @default.
• W2922388521 countsByYear W29223885212021 @default.
• W2922388521 crossrefType "posted-content" @default.
• W2922388521 hasAuthorship W2922388521A5036340517 @default.
• W2922388521 hasAuthorship W2922388521A5038908529 @default.
• W2922388521 hasAuthorship W2922388521A5055864987 @default.
• W2922388521 hasAuthorship W2922388521A5071878141 @default.
• W2922388521 hasAuthorship W2922388521A5084499878 @default.
• W2922388521 hasBestOaLocation W29223885211 @default.
• W2922388521 hasConcept C111919701 @default.
• W2922388521 hasConcept C119857082 @default.
• W2922388521 hasConcept C127413603 @default.
• W2922388521 hasConcept C134306372 @default.
• W2922388521 hasConcept C154945302 @default.
• W2922388521 hasConcept C15744967 @default.
• W2922388521 hasConcept C166957645 @default.
• W2922388521 hasConcept C201995342 @default.
• W2922388521 hasConcept C2775924081 @default.
• W2922388521 hasConcept C2780451532 @default.
• W2922388521 hasConcept C2985564149 @default.
• W2922388521 hasConcept C33923547 @default.
• W2922388521 hasConcept C41008148 @default.
• W2922388521 hasConcept C68387754 @default.
• W2922388521 hasConcept C75306776 @default.
• W2922388521 hasConcept C77805123 @default.
• W2922388521 hasConcept C79581498 @default.
• W2922388521 hasConcept C95457728 @default.
• W2922388521 hasConcept C97541855 @default.
• W2922388521 hasConceptScore W2922388521C111919701 @default.
• W2922388521 hasConceptScore W2922388521C119857082 @default.
• W2922388521 hasConceptScore W2922388521C127413603 @default.
• W2922388521 hasConceptScore W2922388521C134306372 @default.
• W2922388521 hasConceptScore W2922388521C154945302 @default.
• W2922388521 hasConceptScore W2922388521C15744967 @default.
• W2922388521 hasConceptScore W2922388521C166957645 @default.
• W2922388521 hasConceptScore W2922388521C201995342 @default.
• W2922388521 hasConceptScore W2922388521C2775924081 @default.
• W2922388521 hasConceptScore W2922388521C2780451532 @default.
• W2922388521 hasConceptScore W2922388521C2985564149 @default.
• W2922388521 hasConceptScore W2922388521C33923547 @default.
• W2922388521 hasConceptScore W2922388521C41008148 @default.
• W2922388521 hasConceptScore W2922388521C68387754 @default.
• W2922388521 hasConceptScore W2922388521C75306776 @default.
• W2922388521 hasConceptScore W2922388521C77805123 @default.
• W2922388521 hasConceptScore W2922388521C79581498 @default.
• W2922388521 hasConceptScore W2922388521C95457728 @default.
• W2922388521 hasConceptScore W2922388521C97541855 @default.

• next