Matches in SemOpenAlex for { <https://semopenalex.org/work/W2771302359> ?p ?o ?g. }
- W2771302359 abstract "It is well established that humans decision making and instrumental control uses multiple systems, some which use habitual action selection and some which require deliberate planning. Deliberate planning systems use predictions of action-outcomes using an internal model of the agent's environment, while habitual action selection systems learn to automate by repeating previously rewarded actions. Habitual control is computationally efficient but may be inflexible in changing environments. Conversely, deliberate planning may be computationally expensive, but flexible in dynamic environments. This paper proposes a general architecture comprising both control paradigms by introducing an arbitrator that controls which subsystem is used at any time. This system is implemented for a target-reaching task with a simulated two-joint robotic arm that comprises a supervised internal model and deep reinforcement learning. Through permutation of target-reaching conditions, we demonstrate that the proposed is capable of rapidly learning kinematics of the system without a priori knowledge, and is robust to (A) changing environmental reward and kinematics, and (B) occluded vision. The arbitrator model is compared to exclusive deliberate planning with the internal model and exclusive habitual control instances of the model. The results show how such a model can harness the benefits of both systems, using fast decisions in reliable circumstances while optimizing performance in changing environments. In addition, the proposed model learns very fast. Finally, the system which includes internal models is able to reach the target under the visual occlusion, while the pure habitual system is unable to operate sufficiently under such conditions." @default.
- W2771302359 created "2017-12-22" @default.
- W2771302359 creator A5004482959 @default.
- W2771302359 creator A5088920905 @default.
- W2771302359 date "2017-12-06" @default.
- W2771302359 modified "2023-09-27" @default.
- W2771302359 title "A Novel Model for Arbitration between Planning and Habitual Control Systems" @default.
- W2771302359 cites W1520127354 @default.
- W2771302359 cites W1559736362 @default.
- W2771302359 cites W1569296262 @default.
- W2771302359 cites W1757796397 @default.
- W2771302359 cites W1804997726 @default.
- W2771302359 cites W1975401347 @default.
- W2771302359 cites W1980035368 @default.
- W2771302359 cites W2017957151 @default.
- W2771302359 cites W2042239418 @default.
- W2771302359 cites W2056566670 @default.
- W2771302359 cites W2081817157 @default.
- W2771302359 cites W2086612554 @default.
- W2771302359 cites W2100677568 @default.
- W2771302359 cites W2105209710 @default.
- W2771302359 cites W2111287509 @default.
- W2771302359 cites W2112707476 @default.
- W2771302359 cites W2117726420 @default.
- W2771302359 cites W2125729286 @default.
- W2771302359 cites W2129299900 @default.
- W2771302359 cites W2134672787 @default.
- W2771302359 cites W2135630072 @default.
- W2771302359 cites W2142616715 @default.
- W2771302359 cites W2145339207 @default.
- W2771302359 cites W2149565728 @default.
- W2771302359 cites W2151137320 @default.
- W2771302359 cites W2157915068 @default.
- W2771302359 cites W2167362547 @default.
- W2771302359 cites W2173248099 @default.
- W2771302359 cites W2184339914 @default.
- W2771302359 cites W2223493585 @default.
- W2771302359 cites W2271840356 @default.
- W2771302359 cites W2436711315 @default.
- W2771302359 hasPublicationYear "2017" @default.
- W2771302359 type Work @default.
- W2771302359 sameAs 2771302359 @default.
- W2771302359 citedByCount "0" @default.
- W2771302359 crossrefType "posted-content" @default.
- W2771302359 hasAuthorship W2771302359A5004482959 @default.
- W2771302359 hasAuthorship W2771302359A5088920905 @default.
- W2771302359 hasConcept C111472728 @default.
- W2771302359 hasConcept C119857082 @default.
- W2771302359 hasConcept C121332964 @default.
- W2771302359 hasConcept C127413603 @default.
- W2771302359 hasConcept C138885662 @default.
- W2771302359 hasConcept C154945302 @default.
- W2771302359 hasConcept C166109690 @default.
- W2771302359 hasConcept C169760540 @default.
- W2771302359 hasConcept C201995342 @default.
- W2771302359 hasConcept C26760741 @default.
- W2771302359 hasConcept C2775924081 @default.
- W2771302359 hasConcept C2780451532 @default.
- W2771302359 hasConcept C2780791683 @default.
- W2771302359 hasConcept C28427503 @default.
- W2771302359 hasConcept C39920418 @default.
- W2771302359 hasConcept C41008148 @default.
- W2771302359 hasConcept C62520636 @default.
- W2771302359 hasConcept C74650414 @default.
- W2771302359 hasConcept C75553542 @default.
- W2771302359 hasConcept C86803240 @default.
- W2771302359 hasConcept C97541855 @default.
- W2771302359 hasConceptScore W2771302359C111472728 @default.
- W2771302359 hasConceptScore W2771302359C119857082 @default.
- W2771302359 hasConceptScore W2771302359C121332964 @default.
- W2771302359 hasConceptScore W2771302359C127413603 @default.
- W2771302359 hasConceptScore W2771302359C138885662 @default.
- W2771302359 hasConceptScore W2771302359C154945302 @default.
- W2771302359 hasConceptScore W2771302359C166109690 @default.
- W2771302359 hasConceptScore W2771302359C169760540 @default.
- W2771302359 hasConceptScore W2771302359C201995342 @default.
- W2771302359 hasConceptScore W2771302359C26760741 @default.
- W2771302359 hasConceptScore W2771302359C2775924081 @default.
- W2771302359 hasConceptScore W2771302359C2780451532 @default.
- W2771302359 hasConceptScore W2771302359C2780791683 @default.
- W2771302359 hasConceptScore W2771302359C28427503 @default.
- W2771302359 hasConceptScore W2771302359C39920418 @default.
- W2771302359 hasConceptScore W2771302359C41008148 @default.
- W2771302359 hasConceptScore W2771302359C62520636 @default.
- W2771302359 hasConceptScore W2771302359C74650414 @default.
- W2771302359 hasConceptScore W2771302359C75553542 @default.
- W2771302359 hasConceptScore W2771302359C86803240 @default.
- W2771302359 hasConceptScore W2771302359C97541855 @default.
- W2771302359 hasLocation W27713023591 @default.
- W2771302359 hasOpenAccess W2771302359 @default.
- W2771302359 hasPrimaryLocation W27713023591 @default.
- W2771302359 hasRelatedWork W1999846231 @default.
- W2771302359 hasRelatedWork W2128467312 @default.
- W2771302359 hasRelatedWork W2513373085 @default.
- W2771302359 hasRelatedWork W2535652371 @default.
- W2771302359 hasRelatedWork W2565122071 @default.
- W2771302359 hasRelatedWork W2759034818 @default.
- W2771302359 hasRelatedWork W2765397130 @default.
- W2771302359 hasRelatedWork W2895958971 @default.
- W2771302359 hasRelatedWork W2898050260 @default.