Matches in SemOpenAlex for { <https://semopenalex.org/work/W3174723276> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W3174723276 endingPage "11271" @default.
- W3174723276 startingPage "11263" @default.
- W3174723276 abstract "Exploration-exploitation is a powerful and practical tool in multi-agent learning (MAL), however, its effects are far from understood. To make progress in this direction, we study a smooth analogue of Q-learning. We start by showing that our learning model has strong theoretical justification as an optimal model for studying exploration-exploitation. Specifically, we prove that smooth Q-learning has bounded regret in arbitrary games for a cost model that explicitly captures the balance between game and exploration costs and that it always converges to the set of quantal-response equilibria (QRE), the standard solution concept for games under bounded rationality, in weighted potential games with heterogeneous learning agents. In our main task, we then turn to measure the effect of exploration in collective system performance. We characterize the geometry of the QRE surface in low-dimensional MAL systems and link our findings with catastrophe (bifurcation) theory. In particular, as the exploration hyperparameter evolves over-time, the system undergoes phase transitions where the number and stability of equilibria can change radically given an infinitesimal change to the exploration parameter. Based on this, we provide a formal theoretical treatment of how tuning the exploration parameter can provably lead to equilibrium selection with both positive as well as negative (and potentially unbounded) effects to system performance." @default.
- W3174723276 created "2021-07-05" @default.
- W3174723276 creator A5048295129 @default.
- W3174723276 creator A5079969658 @default.
- W3174723276 date "2021-05-18" @default.
- W3174723276 modified "2023-10-16" @default.
- W3174723276 title "Exploration-Exploitation in Multi-Agent Learning: Catastrophe Theory Meets Game Theory" @default.
- W3174723276 doi "https://doi.org/10.1609/aaai.v35i13.17343" @default.
- W3174723276 hasPublicationYear "2021" @default.
- W3174723276 type Work @default.
- W3174723276 sameAs 3174723276 @default.
- W3174723276 citedByCount "3" @default.
- W3174723276 countsByYear W31747232762022 @default.
- W3174723276 countsByYear W31747232762023 @default.
- W3174723276 crossrefType "journal-article" @default.
- W3174723276 hasAuthorship W3174723276A5048295129 @default.
- W3174723276 hasAuthorship W3174723276A5079969658 @default.
- W3174723276 hasBestOaLocation W31747232761 @default.
- W3174723276 hasConcept C112972136 @default.
- W3174723276 hasConcept C119857082 @default.
- W3174723276 hasConcept C126255220 @default.
- W3174723276 hasConcept C134306372 @default.
- W3174723276 hasConcept C144237770 @default.
- W3174723276 hasConcept C154945302 @default.
- W3174723276 hasConcept C177142836 @default.
- W3174723276 hasConcept C177264268 @default.
- W3174723276 hasConcept C199360897 @default.
- W3174723276 hasConcept C31772880 @default.
- W3174723276 hasConcept C33923547 @default.
- W3174723276 hasConcept C34388435 @default.
- W3174723276 hasConcept C41008148 @default.
- W3174723276 hasConcept C50817715 @default.
- W3174723276 hasConcept C58694771 @default.
- W3174723276 hasConcept C91229774 @default.
- W3174723276 hasConceptScore W3174723276C112972136 @default.
- W3174723276 hasConceptScore W3174723276C119857082 @default.
- W3174723276 hasConceptScore W3174723276C126255220 @default.
- W3174723276 hasConceptScore W3174723276C134306372 @default.
- W3174723276 hasConceptScore W3174723276C144237770 @default.
- W3174723276 hasConceptScore W3174723276C154945302 @default.
- W3174723276 hasConceptScore W3174723276C177142836 @default.
- W3174723276 hasConceptScore W3174723276C177264268 @default.
- W3174723276 hasConceptScore W3174723276C199360897 @default.
- W3174723276 hasConceptScore W3174723276C31772880 @default.
- W3174723276 hasConceptScore W3174723276C33923547 @default.
- W3174723276 hasConceptScore W3174723276C34388435 @default.
- W3174723276 hasConceptScore W3174723276C41008148 @default.
- W3174723276 hasConceptScore W3174723276C50817715 @default.
- W3174723276 hasConceptScore W3174723276C58694771 @default.
- W3174723276 hasConceptScore W3174723276C91229774 @default.
- W3174723276 hasIssue "13" @default.
- W3174723276 hasLocation W31747232761 @default.
- W3174723276 hasLocation W31747232762 @default.
- W3174723276 hasLocation W31747232763 @default.
- W3174723276 hasLocation W31747232764 @default.
- W3174723276 hasLocation W31747232765 @default.
- W3174723276 hasLocation W31747232766 @default.
- W3174723276 hasOpenAccess W3174723276 @default.
- W3174723276 hasPrimaryLocation W31747232761 @default.
- W3174723276 hasRelatedWork W1578982440 @default.
- W3174723276 hasRelatedWork W193328375 @default.
- W3174723276 hasRelatedWork W1981486214 @default.
- W3174723276 hasRelatedWork W2082366297 @default.
- W3174723276 hasRelatedWork W2143280270 @default.
- W3174723276 hasRelatedWork W2363014403 @default.
- W3174723276 hasRelatedWork W304213739 @default.
- W3174723276 hasRelatedWork W3125794467 @default.
- W3174723276 hasRelatedWork W3174723276 @default.
- W3174723276 hasRelatedWork W4287556905 @default.
- W3174723276 hasVolume "35" @default.
- W3174723276 isParatext "false" @default.
- W3174723276 isRetracted "false" @default.
- W3174723276 magId "3174723276" @default.
- W3174723276 workType "article" @default.