Matches in SemOpenAlex for { <https://semopenalex.org/work/W3199630126> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3199630126 endingPage "504" @default.
- W3199630126 startingPage "493" @default.
- W3199630126 abstract "The cooperation among AI systems, and between AI systems and humans is becoming increasingly important. In various real-world tasks, an agent needs to cooperate with unknown partner agent types. This requires the agent to assess the behaviour of the partner agent during a cooperative task and to adjust its own policy to support the cooperation. Deep reinforcement learning models can be trained to deliver the required functionality but are known to suffer from sample inefficiency and slow learning. However, adapting to a partner agent behaviour during the ongoing task requires ability to assess the partner agent type quickly. We suggest a method, where we synthetically produce populations of agents with different behavioural patterns together with ground truth data of their behaviour, and use this data for training a meta-learner. We additionally suggest an agent architecture, which can efficiently use the generated data and gain the meta-learning capability. When an agent is equipped with such a meta-learner, it is capable of quickly adapting to cooperation with unknown partner agent types in new situations. This method can be used to automatically form a task distribution for meta-training from emerging behaviours that arise, for example, through self-play." @default.
- W3199630126 created "2021-09-27" @default.
- W3199630126 creator A5018305257 @default.
- W3199630126 creator A5024177833 @default.
- W3199630126 creator A5049661895 @default.
- W3199630126 creator A5052044346 @default.
- W3199630126 creator A5061369039 @default.
- W3199630126 date "2021-01-01" @default.
- W3199630126 modified "2023-10-17" @default.
- W3199630126 title "Behaviour-Conditioned Policies for Cooperative Reinforcement Learning Tasks" @default.
- W3199630126 cites W1571815258 @default.
- W3199630126 cites W2064675550 @default.
- W3199630126 cites W2107878631 @default.
- W3199630126 cites W2141538250 @default.
- W3199630126 cites W2159056499 @default.
- W3199630126 cites W2257979135 @default.
- W3199630126 cites W2292533394 @default.
- W3199630126 cites W2594035753 @default.
- W3199630126 cites W2617547828 @default.
- W3199630126 cites W2758442112 @default.
- W3199630126 cites W2908261578 @default.
- W3199630126 cites W4231746564 @default.
- W3199630126 doi "https://doi.org/10.1007/978-3-030-86380-7_40" @default.
- W3199630126 hasPublicationYear "2021" @default.
- W3199630126 type Work @default.
- W3199630126 sameAs 3199630126 @default.
- W3199630126 citedByCount "1" @default.
- W3199630126 countsByYear W31996301262023 @default.
- W3199630126 crossrefType "book-chapter" @default.
- W3199630126 hasAuthorship W3199630126A5018305257 @default.
- W3199630126 hasAuthorship W3199630126A5024177833 @default.
- W3199630126 hasAuthorship W3199630126A5049661895 @default.
- W3199630126 hasAuthorship W3199630126A5052044346 @default.
- W3199630126 hasAuthorship W3199630126A5061369039 @default.
- W3199630126 hasBestOaLocation W31996301262 @default.
- W3199630126 hasConcept C107457646 @default.
- W3199630126 hasConcept C119857082 @default.
- W3199630126 hasConcept C154945302 @default.
- W3199630126 hasConcept C15744967 @default.
- W3199630126 hasConcept C162324750 @default.
- W3199630126 hasConcept C175444787 @default.
- W3199630126 hasConcept C187736073 @default.
- W3199630126 hasConcept C2778869765 @default.
- W3199630126 hasConcept C2780451532 @default.
- W3199630126 hasConcept C41008148 @default.
- W3199630126 hasConcept C67203356 @default.
- W3199630126 hasConcept C77805123 @default.
- W3199630126 hasConcept C97541855 @default.
- W3199630126 hasConceptScore W3199630126C107457646 @default.
- W3199630126 hasConceptScore W3199630126C119857082 @default.
- W3199630126 hasConceptScore W3199630126C154945302 @default.
- W3199630126 hasConceptScore W3199630126C15744967 @default.
- W3199630126 hasConceptScore W3199630126C162324750 @default.
- W3199630126 hasConceptScore W3199630126C175444787 @default.
- W3199630126 hasConceptScore W3199630126C187736073 @default.
- W3199630126 hasConceptScore W3199630126C2778869765 @default.
- W3199630126 hasConceptScore W3199630126C2780451532 @default.
- W3199630126 hasConceptScore W3199630126C41008148 @default.
- W3199630126 hasConceptScore W3199630126C67203356 @default.
- W3199630126 hasConceptScore W3199630126C77805123 @default.
- W3199630126 hasConceptScore W3199630126C97541855 @default.
- W3199630126 hasLocation W31996301261 @default.
- W3199630126 hasLocation W31996301262 @default.
- W3199630126 hasOpenAccess W3199630126 @default.
- W3199630126 hasPrimaryLocation W31996301261 @default.
- W3199630126 hasRelatedWork W2047937115 @default.
- W3199630126 hasRelatedWork W2774891019 @default.
- W3199630126 hasRelatedWork W2902347140 @default.
- W3199630126 hasRelatedWork W3009692840 @default.
- W3199630126 hasRelatedWork W3022038857 @default.
- W3199630126 hasRelatedWork W3199630126 @default.
- W3199630126 hasRelatedWork W3210581647 @default.
- W3199630126 hasRelatedWork W4286911775 @default.
- W3199630126 hasRelatedWork W4287626175 @default.
- W3199630126 hasRelatedWork W4319083788 @default.
- W3199630126 isParatext "false" @default.
- W3199630126 isRetracted "false" @default.
- W3199630126 magId "3199630126" @default.
- W3199630126 workType "book-chapter" @default.