Matches in SemOpenAlex for { <https://semopenalex.org/work/W4315798539> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4315798539 abstract "Reinforcement Learning formalises an embodied agent's interaction with the environment through observations, rewards and actions. But where do the actions come from? Actions are often considered to represent something external, such as the movement of a limb, a chess piece, or more generally, the output of an actuator. In this work we explore and formalize a contrasting view, namely that actions are best thought of as the output of a sequence of internal choices with respect to an action model. This view is particularly well-suited for leveraging the recent advances in large sequence models as prior knowledge for multi-task reinforcement learning problems. Our main contribution in this work is to show how to augment the standard MDP formalism with a sequential notion of internal action using information-theoretic techniques, and that this leads to self-consistent definitions of both internal and external action value functions." @default.
- W4315798539 created "2023-01-13" @default.
- W4315798539 creator A5020795308 @default.
- W4315798539 creator A5060709021 @default.
- W4315798539 creator A5073944062 @default.
- W4315798539 date "2021-09-30" @default.
- W4315798539 modified "2023-09-26" @default.
- W4315798539 title "Reinforcement Learning with Information-Theoretic Actuation" @default.
- W4315798539 doi "https://doi.org/10.48550/arxiv.2109.15147" @default.
- W4315798539 hasPublicationYear "2021" @default.
- W4315798539 type Work @default.
- W4315798539 citedByCount "0" @default.
- W4315798539 crossrefType "posted-content" @default.
- W4315798539 hasAuthorship W4315798539A5020795308 @default.
- W4315798539 hasAuthorship W4315798539A5060709021 @default.
- W4315798539 hasAuthorship W4315798539A5073944062 @default.
- W4315798539 hasBestOaLocation W43157985391 @default.
- W4315798539 hasConcept C100609095 @default.
- W4315798539 hasConcept C107457646 @default.
- W4315798539 hasConcept C121332964 @default.
- W4315798539 hasConcept C127413603 @default.
- W4315798539 hasConcept C142362112 @default.
- W4315798539 hasConcept C153349607 @default.
- W4315798539 hasConcept C154945302 @default.
- W4315798539 hasConcept C15744967 @default.
- W4315798539 hasConcept C188147891 @default.
- W4315798539 hasConcept C2778112365 @default.
- W4315798539 hasConcept C2780791683 @default.
- W4315798539 hasConcept C41008148 @default.
- W4315798539 hasConcept C54355233 @default.
- W4315798539 hasConcept C558565934 @default.
- W4315798539 hasConcept C62520636 @default.
- W4315798539 hasConcept C66938386 @default.
- W4315798539 hasConcept C67203356 @default.
- W4315798539 hasConcept C73301696 @default.
- W4315798539 hasConcept C86803240 @default.
- W4315798539 hasConcept C97541855 @default.
- W4315798539 hasConceptScore W4315798539C100609095 @default.
- W4315798539 hasConceptScore W4315798539C107457646 @default.
- W4315798539 hasConceptScore W4315798539C121332964 @default.
- W4315798539 hasConceptScore W4315798539C127413603 @default.
- W4315798539 hasConceptScore W4315798539C142362112 @default.
- W4315798539 hasConceptScore W4315798539C153349607 @default.
- W4315798539 hasConceptScore W4315798539C154945302 @default.
- W4315798539 hasConceptScore W4315798539C15744967 @default.
- W4315798539 hasConceptScore W4315798539C188147891 @default.
- W4315798539 hasConceptScore W4315798539C2778112365 @default.
- W4315798539 hasConceptScore W4315798539C2780791683 @default.
- W4315798539 hasConceptScore W4315798539C41008148 @default.
- W4315798539 hasConceptScore W4315798539C54355233 @default.
- W4315798539 hasConceptScore W4315798539C558565934 @default.
- W4315798539 hasConceptScore W4315798539C62520636 @default.
- W4315798539 hasConceptScore W4315798539C66938386 @default.
- W4315798539 hasConceptScore W4315798539C67203356 @default.
- W4315798539 hasConceptScore W4315798539C73301696 @default.
- W4315798539 hasConceptScore W4315798539C86803240 @default.
- W4315798539 hasConceptScore W4315798539C97541855 @default.
- W4315798539 hasLocation W43157985391 @default.
- W4315798539 hasOpenAccess W4315798539 @default.
- W4315798539 hasPrimaryLocation W43157985391 @default.
- W4315798539 hasRelatedWork W1499571508 @default.
- W4315798539 hasRelatedWork W2026813667 @default.
- W4315798539 hasRelatedWork W2041797935 @default.
- W4315798539 hasRelatedWork W2059043110 @default.
- W4315798539 hasRelatedWork W2060348782 @default.
- W4315798539 hasRelatedWork W2095702936 @default.
- W4315798539 hasRelatedWork W2129452909 @default.
- W4315798539 hasRelatedWork W2486533162 @default.
- W4315798539 hasRelatedWork W2586406207 @default.
- W4315798539 hasRelatedWork W2924136311 @default.
- W4315798539 isParatext "false" @default.
- W4315798539 isRetracted "false" @default.
- W4315798539 workType "article" @default.