Matches in SemOpenAlex for { <https://semopenalex.org/work/W3098253476> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3098253476 abstract "One of the common ways children learn is by mimicking adults. Imitation learning focuses on learning policies with suitable performance from demonstrations generated by an expert, with an unspecified performance measure, and unobserved reward signal. Popular methods for imitation learning start by either directly mimicking the behavior policy of an expert (behavior cloning) or by learning a reward function that prioritizes observed expert trajectories (inverse reinforcement learning). However, these methods rely on the assumption that covariates used by the expert to determine her/his actions are fully observed. In this paper, we relax this assumption and study imitation learning when sensory inputs of the learner and the expert differ. First, we provide a non-parametric, graphical criterion that is complete (both necessary and sufficient) for determining the feasibility of imitation from the combinations of demonstration data and qualitative assumptions about the underlying environment, represented in the form of a causal model. We then show that when such a criterion does not hold, imitation could still be feasible by exploiting quantitative knowledge of the expert trajectories. Finally, we develop an efficient procedure for learning the imitating policy from experts' trajectories." @default.
- W3098253476 created "2020-11-23" @default.
- W3098253476 creator A5039620960 @default.
- W3098253476 creator A5073561270 @default.
- W3098253476 creator A5081473407 @default.
- W3098253476 date "2022-08-12" @default.
- W3098253476 modified "2023-09-24" @default.
- W3098253476 title "Causal Imitation Learning with Unobserved Confounders" @default.
- W3098253476 cites W1511986666 @default.
- W3098253476 cites W1524326598 @default.
- W3098253476 cites W1673419196 @default.
- W3098253476 cites W1684361744 @default.
- W3098253476 cites W174918813 @default.
- W3098253476 cites W188311448 @default.
- W3098253476 cites W1986014385 @default.
- W3098253476 cites W1999874108 @default.
- W3098253476 cites W2012204020 @default.
- W3098253476 cites W2061562262 @default.
- W3098253476 cites W2098774185 @default.
- W3098253476 cites W2099471712 @default.
- W3098253476 cites W2113023245 @default.
- W3098253476 cites W2121863487 @default.
- W3098253476 cites W2133233905 @default.
- W3098253476 cites W2143891888 @default.
- W3098253476 cites W2150291618 @default.
- W3098253476 cites W2166944917 @default.
- W3098253476 cites W2167224731 @default.
- W3098253476 cites W2405723472 @default.
- W3098253476 cites W2466989778 @default.
- W3098253476 cites W2604382266 @default.
- W3098253476 cites W2773721443 @default.
- W3098253476 cites W2794908222 @default.
- W3098253476 cites W2896642734 @default.
- W3098253476 cites W2904362269 @default.
- W3098253476 cites W2962958748 @default.
- W3098253476 cites W2966828215 @default.
- W3098253476 cites W2989897153 @default.
- W3098253476 cites W2998275867 @default.
- W3098253476 cites W3008637786 @default.
- W3098253476 doi "https://doi.org/10.48550/arxiv.2208.06267" @default.
- W3098253476 hasPublicationYear "2022" @default.
- W3098253476 type Work @default.
- W3098253476 sameAs 3098253476 @default.
- W3098253476 citedByCount "9" @default.
- W3098253476 countsByYear W30982534762021 @default.
- W3098253476 crossrefType "posted-content" @default.
- W3098253476 hasAuthorship W3098253476A5039620960 @default.
- W3098253476 hasAuthorship W3098253476A5073561270 @default.
- W3098253476 hasAuthorship W3098253476A5081473407 @default.
- W3098253476 hasBestOaLocation W30982534761 @default.
- W3098253476 hasConcept C119857082 @default.
- W3098253476 hasConcept C126388530 @default.
- W3098253476 hasConcept C154945302 @default.
- W3098253476 hasConcept C15744967 @default.
- W3098253476 hasConcept C180747234 @default.
- W3098253476 hasConcept C41008148 @default.
- W3098253476 hasConcept C77805123 @default.
- W3098253476 hasConceptScore W3098253476C119857082 @default.
- W3098253476 hasConceptScore W3098253476C126388530 @default.
- W3098253476 hasConceptScore W3098253476C154945302 @default.
- W3098253476 hasConceptScore W3098253476C15744967 @default.
- W3098253476 hasConceptScore W3098253476C180747234 @default.
- W3098253476 hasConceptScore W3098253476C41008148 @default.
- W3098253476 hasConceptScore W3098253476C77805123 @default.
- W3098253476 hasLocation W30982534761 @default.
- W3098253476 hasOpenAccess W3098253476 @default.
- W3098253476 hasPrimaryLocation W30982534761 @default.
- W3098253476 hasRelatedWork W2415731916 @default.
- W3098253476 hasRelatedWork W2765889516 @default.
- W3098253476 hasRelatedWork W2961085424 @default.
- W3098253476 hasRelatedWork W3046775127 @default.
- W3098253476 hasRelatedWork W3107474891 @default.
- W3098253476 hasRelatedWork W3136151093 @default.
- W3098253476 hasRelatedWork W4205958290 @default.
- W3098253476 hasRelatedWork W4283077296 @default.
- W3098253476 hasRelatedWork W4286629047 @default.
- W3098253476 hasRelatedWork W4224009465 @default.
- W3098253476 isParatext "false" @default.
- W3098253476 isRetracted "false" @default.
- W3098253476 magId "3098253476" @default.
- W3098253476 workType "article" @default.