Matches in SemOpenAlex for { <https://semopenalex.org/work/W4206520121> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4206520121 endingPage "1291" @default.
- W4206520121 startingPage "1284" @default.
- W4206520121 abstract "Efficiently learning interpretable policies for complex tasks from demonstrations is a challenging problem. We present Hierarchical Inference with Logical Options (HILO), a novel learning algorithm that learns to imitate expert demonstrations by learning the rules that the expert is following. The rules are represented as linear temporal logic (LTL) formulas, which are interpretable and capable of encoding complex behaviors. Unlike previous works, which learn rules from high-level propositions, HILO learns rules by taking both propositions and low-level trajectories as input. It does this by defining a Bayesian model over LTL formulas, propositions, and low-level trajectories. The Bayesian model bridges the gap from formula to low-level trajectory by using a planner to find an optimal policy for a given LTL formula. Stochastic variational inference is then used to find a posterior distribution over formulas and policies given expert demonstrations. We show that by learning rules from both propositions and low-level states, HILO outperforms previous work on a rule-learning task and on four planning tasks while needing less data. We also validate HILO in the real world by teaching a robotic arm a complex packing task." @default.
- W4206520121 created "2022-01-26" @default.
- W4206520121 creator A5006883016 @default.
- W4206520121 creator A5035339773 @default.
- W4206520121 creator A5053151494 @default.
- W4206520121 creator A5066830185 @default.
- W4206520121 creator A5067958726 @default.
- W4206520121 date "2022-04-01" @default.
- W4206520121 modified "2023-10-16" @default.
- W4206520121 title "Learning Policies by Learning Rules" @default.
- W4206520121 cites W1999874108 @default.
- W4206520121 cites W2063471043 @default.
- W4206520121 cites W2522043470 @default.
- W4206520121 cites W2787066086 @default.
- W4206520121 cites W2965569070 @default.
- W4206520121 cites W2966183138 @default.
- W4206520121 cites W2998509800 @default.
- W4206520121 cites W3038945966 @default.
- W4206520121 cites W3089728370 @default.
- W4206520121 doi "https://doi.org/10.1109/lra.2021.3139380" @default.
- W4206520121 hasPublicationYear "2022" @default.
- W4206520121 type Work @default.
- W4206520121 citedByCount "0" @default.
- W4206520121 crossrefType "journal-article" @default.
- W4206520121 hasAuthorship W4206520121A5006883016 @default.
- W4206520121 hasAuthorship W4206520121A5035339773 @default.
- W4206520121 hasAuthorship W4206520121A5053151494 @default.
- W4206520121 hasAuthorship W4206520121A5066830185 @default.
- W4206520121 hasAuthorship W4206520121A5067958726 @default.
- W4206520121 hasBestOaLocation W42065201211 @default.
- W4206520121 hasConcept C107673813 @default.
- W4206520121 hasConcept C119857082 @default.
- W4206520121 hasConcept C154945302 @default.
- W4206520121 hasConcept C160234255 @default.
- W4206520121 hasConcept C162324750 @default.
- W4206520121 hasConcept C187736073 @default.
- W4206520121 hasConcept C2776214188 @default.
- W4206520121 hasConcept C2776999362 @default.
- W4206520121 hasConcept C2777472644 @default.
- W4206520121 hasConcept C2780451532 @default.
- W4206520121 hasConcept C41008148 @default.
- W4206520121 hasConceptScore W4206520121C107673813 @default.
- W4206520121 hasConceptScore W4206520121C119857082 @default.
- W4206520121 hasConceptScore W4206520121C154945302 @default.
- W4206520121 hasConceptScore W4206520121C160234255 @default.
- W4206520121 hasConceptScore W4206520121C162324750 @default.
- W4206520121 hasConceptScore W4206520121C187736073 @default.
- W4206520121 hasConceptScore W4206520121C2776214188 @default.
- W4206520121 hasConceptScore W4206520121C2776999362 @default.
- W4206520121 hasConceptScore W4206520121C2777472644 @default.
- W4206520121 hasConceptScore W4206520121C2780451532 @default.
- W4206520121 hasConceptScore W4206520121C41008148 @default.
- W4206520121 hasFunder F4320308782 @default.
- W4206520121 hasFunder F4320315934 @default.
- W4206520121 hasFunder F4320316620 @default.
- W4206520121 hasFunder F4320335353 @default.
- W4206520121 hasIssue "2" @default.
- W4206520121 hasLocation W42065201211 @default.
- W4206520121 hasLocation W42065201212 @default.
- W4206520121 hasOpenAccess W4206520121 @default.
- W4206520121 hasPrimaryLocation W42065201211 @default.
- W4206520121 hasRelatedWork W2099667085 @default.
- W4206520121 hasRelatedWork W2183617661 @default.
- W4206520121 hasRelatedWork W2511279186 @default.
- W4206520121 hasRelatedWork W2532368719 @default.
- W4206520121 hasRelatedWork W2753218748 @default.
- W4206520121 hasRelatedWork W2774409638 @default.
- W4206520121 hasRelatedWork W2963058055 @default.
- W4206520121 hasRelatedWork W3029748970 @default.
- W4206520121 hasRelatedWork W4206520121 @default.
- W4206520121 hasRelatedWork W981988864 @default.
- W4206520121 hasVolume "7" @default.
- W4206520121 isParatext "false" @default.
- W4206520121 isRetracted "false" @default.
- W4206520121 workType "article" @default.