Matches in SemOpenAlex for { <https://semopenalex.org/work/W2991934429> ?p ?o ?g. }
- W2991934429 abstract "We study learning control in an online reset-free lifelong learning scenario, where mistakes can compound catastrophically into the future and the underlying dynamics of the environment may change. Traditional model-free policy learning methods have achieved successes in difficult tasks due to their broad flexibility, but struggle in this setting, as they can activate failure modes early in their lifetimes which are difficult to recover from and face performance degradation as dynamics change. On the other hand, model-based planning methods learn and adapt quickly, but require prohibitive levels of computational resources. We present a new algorithm, Adaptive Online Planning (AOP), that achieves strong performance in this setting by combining model-based planning with model-free learning. By approximating the uncertainty of the model-free components and the planner performance, AOP is able to call upon more extensive planning only when necessary, leading to reduced computation times, while still gracefully adapting behaviors in the face of unpredictable changes in the world -- even when traditional RL fails." @default.
- W2991934429 created "2019-12-13" @default.
- W2991934429 creator A5014193325 @default.
- W2991934429 creator A5036548399 @default.
- W2991934429 creator A5049349154 @default.
- W2991934429 date "2019-09-25" @default.
- W2991934429 modified "2023-09-29" @default.
- W2991934429 title "Adaptive Online Planning for Continual Lifelong Learning" @default.
- W2991934429 cites W1519626139 @default.
- W2991934429 cites W1591393094 @default.
- W2991934429 cites W1757796397 @default.
- W2991934429 cites W2043787485 @default.
- W2991934429 cites W2104733512 @default.
- W2991934429 cites W2113839990 @default.
- W2991934429 cites W2123459560 @default.
- W2991934429 cites W2167362547 @default.
- W2991934429 cites W2169323873 @default.
- W2991934429 cites W2186601217 @default.
- W2991934429 cites W2280163991 @default.
- W2991934429 cites W2489939061 @default.
- W2991934429 cites W2560647685 @default.
- W2991934429 cites W2618097077 @default.
- W2991934429 cites W2736601468 @default.
- W2991934429 cites W2757631751 @default.
- W2991934429 cites W2785389871 @default.
- W2991934429 cites W2785962646 @default.
- W2991934429 cites W2787074649 @default.
- W2991934429 cites W2787938642 @default.
- W2991934429 cites W2788388592 @default.
- W2991934429 cites W2805762288 @default.
- W2991934429 cites W2808335646 @default.
- W2991934429 cites W2810754397 @default.
- W2991934429 cites W2892230114 @default.
- W2991934429 cites W2898917980 @default.
- W2991934429 cites W2902456977 @default.
- W2991934429 cites W2904453761 @default.
- W2991934429 cites W2939137134 @default.
- W2991934429 cites W2950564923 @default.
- W2991934429 cites W2950624398 @default.
- W2991934429 cites W2962723954 @default.
- W2991934429 cites W2962749646 @default.
- W2991934429 cites W2962872206 @default.
- W2991934429 cites W2963598363 @default.
- W2991934429 cites W2964093801 @default.
- W2991934429 cites W3037207827 @default.
- W2991934429 cites W3091453419 @default.
- W2991934429 cites W3123661679 @default.
- W2991934429 hasPublicationYear "2019" @default.
- W2991934429 type Work @default.
- W2991934429 sameAs 2991934429 @default.
- W2991934429 citedByCount "10" @default.
- W2991934429 countsByYear W29919344292019 @default.
- W2991934429 countsByYear W29919344292020 @default.
- W2991934429 countsByYear W29919344292021 @default.
- W2991934429 countsByYear W29919344292023 @default.
- W2991934429 crossrefType "posted-content" @default.
- W2991934429 hasAuthorship W2991934429A5014193325 @default.
- W2991934429 hasAuthorship W2991934429A5036548399 @default.
- W2991934429 hasAuthorship W2991934429A5049349154 @default.
- W2991934429 hasConcept C105795698 @default.
- W2991934429 hasConcept C106159729 @default.
- W2991934429 hasConcept C108771440 @default.
- W2991934429 hasConcept C144024400 @default.
- W2991934429 hasConcept C154945302 @default.
- W2991934429 hasConcept C15744967 @default.
- W2991934429 hasConcept C162324750 @default.
- W2991934429 hasConcept C19417346 @default.
- W2991934429 hasConcept C2775924081 @default.
- W2991934429 hasConcept C2776999362 @default.
- W2991934429 hasConcept C2777851325 @default.
- W2991934429 hasConcept C2779304628 @default.
- W2991934429 hasConcept C2779795794 @default.
- W2991934429 hasConcept C2780598303 @default.
- W2991934429 hasConcept C33923547 @default.
- W2991934429 hasConcept C36289849 @default.
- W2991934429 hasConcept C41008148 @default.
- W2991934429 hasConcept C97541855 @default.
- W2991934429 hasConceptScore W2991934429C105795698 @default.
- W2991934429 hasConceptScore W2991934429C106159729 @default.
- W2991934429 hasConceptScore W2991934429C108771440 @default.
- W2991934429 hasConceptScore W2991934429C144024400 @default.
- W2991934429 hasConceptScore W2991934429C154945302 @default.
- W2991934429 hasConceptScore W2991934429C15744967 @default.
- W2991934429 hasConceptScore W2991934429C162324750 @default.
- W2991934429 hasConceptScore W2991934429C19417346 @default.
- W2991934429 hasConceptScore W2991934429C2775924081 @default.
- W2991934429 hasConceptScore W2991934429C2776999362 @default.
- W2991934429 hasConceptScore W2991934429C2777851325 @default.
- W2991934429 hasConceptScore W2991934429C2779304628 @default.
- W2991934429 hasConceptScore W2991934429C2779795794 @default.
- W2991934429 hasConceptScore W2991934429C2780598303 @default.
- W2991934429 hasConceptScore W2991934429C33923547 @default.
- W2991934429 hasConceptScore W2991934429C36289849 @default.
- W2991934429 hasConceptScore W2991934429C41008148 @default.
- W2991934429 hasConceptScore W2991934429C97541855 @default.
- W2991934429 hasLocation W29919344291 @default.
- W2991934429 hasOpenAccess W2991934429 @default.
- W2991934429 hasPrimaryLocation W29919344291 @default.
- W2991934429 hasRelatedWork W1696165702 @default.
- W2991934429 hasRelatedWork W2059708850 @default.