Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201551014> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W3201551014 abstract "The ability of an AI agent to assist other agents, such as humans, is an important and challenging goal, which requires the assisting agent to reason about the behavior and infer the goals of the assisted agent. Training such an ability by using reinforcement learning usually requires large amounts of online training, which is difficult and costly. On the other hand, offline data about the behavior of the assisted agent might be available, but is non-trivial to take advantage of by methods such as offline reinforcement learning. We introduce methods where the capability to create a representation of the behavior is first pre-trained with offline data, after which only a small amount of interaction data is needed to learn an assisting policy. We test the setting in a gridworld where the helper agent has the capability to manipulate the environment of the assisted artificial agents, and introduce three different scenarios where the assistance considerably improves the performance of the assisted agents." @default.
- W3201551014 created "2021-09-27" @default.
- W3201551014 creator A5018305257 @default.
- W3201551014 creator A5024177833 @default.
- W3201551014 creator A5049661895 @default.
- W3201551014 creator A5061369039 @default.
- W3201551014 date "2021-01-01" @default.
- W3201551014 modified "2023-09-26" @default.
- W3201551014 title "Learning to Assist Agents by Observing Them" @default.
- W3201551014 cites W2091118421 @default.
- W3201551014 cites W2141538250 @default.
- W3201551014 cites W2154851666 @default.
- W3201551014 cites W2161381512 @default.
- W3201551014 cites W2165698076 @default.
- W3201551014 cites W2292533394 @default.
- W3201551014 cites W2594035753 @default.
- W3201551014 cites W2758442112 @default.
- W3201551014 cites W4231746564 @default.
- W3201551014 doi "https://doi.org/10.1007/978-3-030-86380-7_42" @default.
- W3201551014 hasPublicationYear "2021" @default.
- W3201551014 type Work @default.
- W3201551014 sameAs 3201551014 @default.
- W3201551014 citedByCount "0" @default.
- W3201551014 crossrefType "book-chapter" @default.
- W3201551014 hasAuthorship W3201551014A5018305257 @default.
- W3201551014 hasAuthorship W3201551014A5024177833 @default.
- W3201551014 hasAuthorship W3201551014A5049661895 @default.
- W3201551014 hasAuthorship W3201551014A5061369039 @default.
- W3201551014 hasBestOaLocation W32015510142 @default.
- W3201551014 hasConcept C107457646 @default.
- W3201551014 hasConcept C119857082 @default.
- W3201551014 hasConcept C154945302 @default.
- W3201551014 hasConcept C17744445 @default.
- W3201551014 hasConcept C199539241 @default.
- W3201551014 hasConcept C2776359362 @default.
- W3201551014 hasConcept C41008148 @default.
- W3201551014 hasConcept C51632099 @default.
- W3201551014 hasConcept C74072328 @default.
- W3201551014 hasConcept C94625758 @default.
- W3201551014 hasConcept C97541855 @default.
- W3201551014 hasConceptScore W3201551014C107457646 @default.
- W3201551014 hasConceptScore W3201551014C119857082 @default.
- W3201551014 hasConceptScore W3201551014C154945302 @default.
- W3201551014 hasConceptScore W3201551014C17744445 @default.
- W3201551014 hasConceptScore W3201551014C199539241 @default.
- W3201551014 hasConceptScore W3201551014C2776359362 @default.
- W3201551014 hasConceptScore W3201551014C41008148 @default.
- W3201551014 hasConceptScore W3201551014C51632099 @default.
- W3201551014 hasConceptScore W3201551014C74072328 @default.
- W3201551014 hasConceptScore W3201551014C94625758 @default.
- W3201551014 hasConceptScore W3201551014C97541855 @default.
- W3201551014 hasLocation W32015510141 @default.
- W3201551014 hasLocation W32015510142 @default.
- W3201551014 hasOpenAccess W3201551014 @default.
- W3201551014 hasPrimaryLocation W32015510141 @default.
- W3201551014 hasRelatedWork W10379689 @default.
- W3201551014 hasRelatedWork W11104910 @default.
- W3201551014 hasRelatedWork W1512436 @default.
- W3201551014 hasRelatedWork W4412456 @default.
- W3201551014 hasRelatedWork W5081013 @default.
- W3201551014 hasRelatedWork W6514950 @default.
- W3201551014 hasRelatedWork W7430954 @default.
- W3201551014 hasRelatedWork W8447228 @default.
- W3201551014 hasRelatedWork W868042 @default.
- W3201551014 hasRelatedWork W929682 @default.
- W3201551014 isParatext "false" @default.
- W3201551014 isRetracted "false" @default.
- W3201551014 magId "3201551014" @default.
- W3201551014 workType "book-chapter" @default.