Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386473802> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4386473802 endingPage "344" @default.
- W4386473802 startingPage "328" @default.
- W4386473802 abstract "Reward machines have recently been proposed as a means of encoding team tasks in cooperative multi-agent reinforcement learning. The resulting multi-agent reward machine is then decomposed into individual reward machines, one for each member of the team, allowing agents to learn in a decentralised manner while still achieving the team task. However, current work assumes the multi-agent reward machine to be given. In this paper, we show how reward machines for team tasks can be synthesised automatically from an Alternating-Time Temporal Logic specification of the desired team behaviour and a high-level abstraction of the agents’ environment. We present results suggesting that our automated approach has comparable, if not better, sample efficiency than reward machines generated by hand for multi-agent tasks." @default.
- W4386473802 created "2023-09-07" @default.
- W4386473802 creator A5028760842 @default.
- W4386473802 creator A5052831741 @default.
- W4386473802 creator A5064693586 @default.
- W4386473802 creator A5092762573 @default.
- W4386473802 date "2023-01-01" @default.
- W4386473802 modified "2023-09-30" @default.
- W4386473802 title "Synthesising Reward Machines for Cooperative Multi-Agent Reinforcement Learning" @default.
- W4386473802 cites W1641379095 @default.
- W4386473802 cites W2031522732 @default.
- W4386473802 cites W2048905609 @default.
- W4386473802 cites W206679605 @default.
- W4386473802 cites W2107544712 @default.
- W4386473802 cites W2813428123 @default.
- W4386473802 cites W2966537673 @default.
- W4386473802 cites W2972500268 @default.
- W4386473802 cites W2981038142 @default.
- W4386473802 cites W2989068617 @default.
- W4386473802 cites W2991046523 @default.
- W4386473802 cites W3037476194 @default.
- W4386473802 cites W3092156990 @default.
- W4386473802 doi "https://doi.org/10.1007/978-3-031-43264-4_21" @default.
- W4386473802 hasPublicationYear "2023" @default.
- W4386473802 type Work @default.
- W4386473802 citedByCount "0" @default.
- W4386473802 crossrefType "book-chapter" @default.
- W4386473802 hasAuthorship W4386473802A5028760842 @default.
- W4386473802 hasAuthorship W4386473802A5052831741 @default.
- W4386473802 hasAuthorship W4386473802A5064693586 @default.
- W4386473802 hasAuthorship W4386473802A5092762573 @default.
- W4386473802 hasConcept C111472728 @default.
- W4386473802 hasConcept C119857082 @default.
- W4386473802 hasConcept C124304363 @default.
- W4386473802 hasConcept C125411270 @default.
- W4386473802 hasConcept C138885662 @default.
- W4386473802 hasConcept C154945302 @default.
- W4386473802 hasConcept C162324750 @default.
- W4386473802 hasConcept C187736073 @default.
- W4386473802 hasConcept C2780451532 @default.
- W4386473802 hasConcept C41008148 @default.
- W4386473802 hasConcept C97541855 @default.
- W4386473802 hasConceptScore W4386473802C111472728 @default.
- W4386473802 hasConceptScore W4386473802C119857082 @default.
- W4386473802 hasConceptScore W4386473802C124304363 @default.
- W4386473802 hasConceptScore W4386473802C125411270 @default.
- W4386473802 hasConceptScore W4386473802C138885662 @default.
- W4386473802 hasConceptScore W4386473802C154945302 @default.
- W4386473802 hasConceptScore W4386473802C162324750 @default.
- W4386473802 hasConceptScore W4386473802C187736073 @default.
- W4386473802 hasConceptScore W4386473802C2780451532 @default.
- W4386473802 hasConceptScore W4386473802C41008148 @default.
- W4386473802 hasConceptScore W4386473802C97541855 @default.
- W4386473802 hasLocation W43864738021 @default.
- W4386473802 hasOpenAccess W4386473802 @default.
- W4386473802 hasPrimaryLocation W43864738021 @default.
- W4386473802 hasRelatedWork W260766989 @default.
- W4386473802 hasRelatedWork W2959276766 @default.
- W4386473802 hasRelatedWork W2961085424 @default.
- W4386473802 hasRelatedWork W3074294383 @default.
- W4386473802 hasRelatedWork W3139193008 @default.
- W4386473802 hasRelatedWork W3216885170 @default.
- W4386473802 hasRelatedWork W4206669594 @default.
- W4386473802 hasRelatedWork W4295941380 @default.
- W4386473802 hasRelatedWork W4306674287 @default.
- W4386473802 hasRelatedWork W4319083788 @default.
- W4386473802 isParatext "false" @default.
- W4386473802 isRetracted "false" @default.
- W4386473802 workType "book-chapter" @default.