Matches in SemOpenAlex for { <https://semopenalex.org/work/W3101379758> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W3101379758 endingPage "7909" @default.
- W3101379758 startingPage "7898" @default.
- W3101379758 abstract "A fundamental question in neuroscience is how the brain creates an internal model of the world to guide actions using sequences of ambiguous sensory information. This is naturally formulated as a reinforcement learning problem under partial observations, where an agent must estimate relevant latent variables in the world from its evidence, anticipate possible future states, and choose actions that optimize total expected reward. This problem can be solved by control theory, which allows us to find the optimal actions for a given system dynamics and objective function. However, animals often appear to behave suboptimally. Why? We hypothesize that animals have their own flawed internal model of the world, and choose actions with the highest expected subjective reward according to that flawed model. We describe this behavior as rational but not optimal. The problem of Inverse Rational Control (IRC) aims to identify which internal model would best explain an agent's actions. Our contribution here generalizes past work on Inverse Rational Control which solved this problem for discrete control in partially observable Markov decision processes. Here we accommodate continuous nonlinear dynamics and continuous actions, and impute sensory observations corrupted by unknown noise that is private to the animal. We first build an optimal Bayesian agent that learns an optimal policy generalized over the entire model space of dynamics and subjective rewards using deep reinforcement learning. Crucially, this allows us to compute a likelihood over models for experimentally observable action trajectories acquired from a suboptimal agent. We then find the model parameters that maximize the likelihood using gradient ascent. Our method successfully recovers the true model of rational agents. This approach provides a foundation for interpreting the behavioral and neural dynamics of animal brains during complex tasks." @default.
- W3101379758 created "2020-11-23" @default.
- W3101379758 creator A5032094381 @default.
- W3101379758 creator A5035328170 @default.
- W3101379758 creator A5057055829 @default.
- W3101379758 creator A5071796726 @default.
- W3101379758 date "2020-12-01" @default.
- W3101379758 modified "2023-09-23" @default.
- W3101379758 title "Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamics." @default.
- W3101379758 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8549572" @default.
- W3101379758 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34712038" @default.
- W3101379758 hasPublicationYear "2020" @default.
- W3101379758 type Work @default.
- W3101379758 sameAs 3101379758 @default.
- W3101379758 citedByCount "5" @default.
- W3101379758 countsByYear W31013797582022 @default.
- W3101379758 countsByYear W31013797582023 @default.
- W3101379758 crossrefType "proceedings-article" @default.
- W3101379758 hasAuthorship W3101379758A5032094381 @default.
- W3101379758 hasAuthorship W3101379758A5035328170 @default.
- W3101379758 hasAuthorship W3101379758A5057055829 @default.
- W3101379758 hasAuthorship W3101379758A5071796726 @default.
- W3101379758 hasConcept C105795698 @default.
- W3101379758 hasConcept C106189395 @default.
- W3101379758 hasConcept C107673813 @default.
- W3101379758 hasConcept C119857082 @default.
- W3101379758 hasConcept C121332964 @default.
- W3101379758 hasConcept C126255220 @default.
- W3101379758 hasConcept C154945302 @default.
- W3101379758 hasConcept C158622935 @default.
- W3101379758 hasConcept C159886148 @default.
- W3101379758 hasConcept C163836022 @default.
- W3101379758 hasConcept C17098449 @default.
- W3101379758 hasConcept C2775924081 @default.
- W3101379758 hasConcept C2780791683 @default.
- W3101379758 hasConcept C28427503 @default.
- W3101379758 hasConcept C32848918 @default.
- W3101379758 hasConcept C33923547 @default.
- W3101379758 hasConcept C41008148 @default.
- W3101379758 hasConcept C62520636 @default.
- W3101379758 hasConcept C72434380 @default.
- W3101379758 hasConcept C91575142 @default.
- W3101379758 hasConcept C97541855 @default.
- W3101379758 hasConcept C98763669 @default.
- W3101379758 hasConceptScore W3101379758C105795698 @default.
- W3101379758 hasConceptScore W3101379758C106189395 @default.
- W3101379758 hasConceptScore W3101379758C107673813 @default.
- W3101379758 hasConceptScore W3101379758C119857082 @default.
- W3101379758 hasConceptScore W3101379758C121332964 @default.
- W3101379758 hasConceptScore W3101379758C126255220 @default.
- W3101379758 hasConceptScore W3101379758C154945302 @default.
- W3101379758 hasConceptScore W3101379758C158622935 @default.
- W3101379758 hasConceptScore W3101379758C159886148 @default.
- W3101379758 hasConceptScore W3101379758C163836022 @default.
- W3101379758 hasConceptScore W3101379758C17098449 @default.
- W3101379758 hasConceptScore W3101379758C2775924081 @default.
- W3101379758 hasConceptScore W3101379758C2780791683 @default.
- W3101379758 hasConceptScore W3101379758C28427503 @default.
- W3101379758 hasConceptScore W3101379758C32848918 @default.
- W3101379758 hasConceptScore W3101379758C33923547 @default.
- W3101379758 hasConceptScore W3101379758C41008148 @default.
- W3101379758 hasConceptScore W3101379758C62520636 @default.
- W3101379758 hasConceptScore W3101379758C72434380 @default.
- W3101379758 hasConceptScore W3101379758C91575142 @default.
- W3101379758 hasConceptScore W3101379758C97541855 @default.
- W3101379758 hasConceptScore W3101379758C98763669 @default.
- W3101379758 hasOpenAccess W3101379758 @default.
- W3101379758 hasRelatedWork W1600460799 @default.
- W3101379758 hasRelatedWork W1794915723 @default.
- W3101379758 hasRelatedWork W2140954027 @default.
- W3101379758 hasRelatedWork W2761792179 @default.
- W3101379758 hasRelatedWork W2795908317 @default.
- W3101379758 hasRelatedWork W2799528510 @default.
- W3101379758 hasRelatedWork W2884970059 @default.
- W3101379758 hasRelatedWork W2930620797 @default.
- W3101379758 hasRelatedWork W2949767349 @default.
- W3101379758 hasRelatedWork W2951056918 @default.
- W3101379758 hasRelatedWork W2952371101 @default.
- W3101379758 hasRelatedWork W2963516265 @default.
- W3101379758 hasRelatedWork W2972468830 @default.
- W3101379758 hasRelatedWork W2973590349 @default.
- W3101379758 hasRelatedWork W2993376733 @default.
- W3101379758 hasRelatedWork W3018754465 @default.
- W3101379758 hasRelatedWork W3033075553 @default.
- W3101379758 hasRelatedWork W3103105396 @default.
- W3101379758 hasRelatedWork W3134916406 @default.
- W3101379758 hasRelatedWork W3157598639 @default.
- W3101379758 hasVolume "33" @default.
- W3101379758 isParatext "false" @default.
- W3101379758 isRetracted "false" @default.
- W3101379758 magId "3101379758" @default.
- W3101379758 workType "article" @default.