FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204164197> ?p ?o ?g. }

• W3204164197 abstract "Reinforcement learning is hard in general. Yet, in many specific environments, learning is easy. What makes learning easy in one environment, but difficult in another? We address this question by proposing a simple measure of reinforcement-learning hardness called the bad-policy density. This quantity measures the fraction of the deterministic stationary policy space that is below a desired threshold in value. We prove that this simple quantity has many properties one would expect of a measure of learning hardness. Further, we prove it is NP-hard to compute the measure in general, but there are paths to polynomial-time approximation. We conclude by summarizing potential directions and uses for this measure." @default.
• W3204164197 created "2021-10-11" @default.
• W3204164197 creator A5009722403 @default.
• W3204164197 creator A5021573603 @default.
• W3204164197 creator A5032791503 @default.
• W3204164197 creator A5061301686 @default.
• W3204164197 creator A5075792734 @default.
• W3204164197 creator A5080191195 @default.
• W3204164197 date "2021-10-07" @default.
• W3204164197 modified "2023-09-27" @default.
• W3204164197 title "Bad-Policy Density: A Measure of Reinforcement Learning Hardness." @default.
• W3204164197 cites W1512919909 @default.
• W3204164197 cites W1662803991 @default.
• W3204164197 cites W1850488217 @default.
• W3204164197 cites W2101355568 @default.
• W3204164197 cites W2106285343 @default.
• W3204164197 cites W2115044435 @default.
• W3204164197 cites W2115293355 @default.
• W3204164197 cites W2120678009 @default.
• W3204164197 cites W2122410182 @default.
• W3204164197 cites W2123447947 @default.
• W3204164197 cites W2132096648 @default.
• W3204164197 cites W2154172448 @default.
• W3204164197 cites W2157864803 @default.
• W3204164197 cites W2163840227 @default.
• W3204164197 cites W2184118689 @default.
• W3204164197 cites W2489939061 @default.
• W3204164197 cites W2545659366 @default.
• W3204164197 cites W2962723383 @default.
• W3204164197 cites W2962847657 @default.
• W3204164197 cites W2963713569 @default.
• W3204164197 cites W2963767098 @default.
• W3204164197 cites W2965004202 @default.
• W3204164197 cites W2990830025 @default.
• W3204164197 cites W2995638039 @default.
• W3204164197 cites W3034360859 @default.
• W3204164197 cites W3037351657 @default.
• W3204164197 cites W3100499156 @default.
• W3204164197 cites W3133622680 @default.
• W3204164197 cites W634962210 @default.
• W3204164197 hasPublicationYear "2021" @default.
• W3204164197 type Work @default.
• W3204164197 sameAs 3204164197 @default.
• W3204164197 citedByCount "0" @default.
• W3204164197 crossrefType "posted-content" @default.
• W3204164197 hasAuthorship W3204164197A5009722403 @default.
• W3204164197 hasAuthorship W3204164197A5021573603 @default.
• W3204164197 hasAuthorship W3204164197A5032791503 @default.
• W3204164197 hasAuthorship W3204164197A5061301686 @default.
• W3204164197 hasAuthorship W3204164197A5075792734 @default.
• W3204164197 hasAuthorship W3204164197A5080191195 @default.
• W3204164197 hasConcept C111472728 @default.
• W3204164197 hasConcept C111919701 @default.
• W3204164197 hasConcept C124101348 @default.
• W3204164197 hasConcept C126255220 @default.
• W3204164197 hasConcept C138885662 @default.
• W3204164197 hasConcept C149629883 @default.
• W3204164197 hasConcept C154945302 @default.
• W3204164197 hasConcept C15744967 @default.
• W3204164197 hasConcept C178790620 @default.
• W3204164197 hasConcept C185592680 @default.
• W3204164197 hasConcept C2778572836 @default.
• W3204164197 hasConcept C2780009758 @default.
• W3204164197 hasConcept C2780586882 @default.
• W3204164197 hasConcept C33923547 @default.
• W3204164197 hasConcept C41008148 @default.
• W3204164197 hasConcept C67203356 @default.
• W3204164197 hasConcept C77805123 @default.
• W3204164197 hasConcept C97541855 @default.
• W3204164197 hasConceptScore W3204164197C111472728 @default.
• W3204164197 hasConceptScore W3204164197C111919701 @default.
• W3204164197 hasConceptScore W3204164197C124101348 @default.
• W3204164197 hasConceptScore W3204164197C126255220 @default.
• W3204164197 hasConceptScore W3204164197C138885662 @default.
• W3204164197 hasConceptScore W3204164197C149629883 @default.
• W3204164197 hasConceptScore W3204164197C154945302 @default.
• W3204164197 hasConceptScore W3204164197C15744967 @default.
• W3204164197 hasConceptScore W3204164197C178790620 @default.
• W3204164197 hasConceptScore W3204164197C185592680 @default.
• W3204164197 hasConceptScore W3204164197C2778572836 @default.
• W3204164197 hasConceptScore W3204164197C2780009758 @default.
• W3204164197 hasConceptScore W3204164197C2780586882 @default.
• W3204164197 hasConceptScore W3204164197C33923547 @default.
• W3204164197 hasConceptScore W3204164197C41008148 @default.
• W3204164197 hasConceptScore W3204164197C67203356 @default.
• W3204164197 hasConceptScore W3204164197C77805123 @default.
• W3204164197 hasConceptScore W3204164197C97541855 @default.
• W3204164197 hasLocation W32041641971 @default.
• W3204164197 hasOpenAccess W3204164197 @default.
• W3204164197 hasPrimaryLocation W32041641971 @default.
• W3204164197 hasRelatedWork W142858861 @default.
• W3204164197 hasRelatedWork W1505837856 @default.
• W3204164197 hasRelatedWork W1616330627 @default.
• W3204164197 hasRelatedWork W2013541926 @default.
• W3204164197 hasRelatedWork W2029870426 @default.
• W3204164197 hasRelatedWork W2217099143 @default.
• W3204164197 hasRelatedWork W2224508600 @default.
• W3204164197 hasRelatedWork W2279189561 @default.
• W3204164197 hasRelatedWork W2775694264 @default.
• W3204164197 hasRelatedWork W2787075019 @default.

• next