Matches in SemOpenAlex for { <https://semopenalex.org/work/W3120022075> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3120022075 abstract "In this work, we study the interaction of strategic agents in continuous action Cournot games with limited information feedback. Cournot game is the essential market model for many socio-economic systems where agents learn and compete without the full knowledge of the system or each other. We consider the dynamics of the policy gradient algorithm, which is a widely adopted continuous control reinforcement learning algorithm, in concave Cournot games. We prove the convergence of policy gradient dynamics to the Nash equilibrium when the price function is linear or the number of agents is two. This is the first result (to the best of our knowledge) on the convergence property of learning algorithms with continuous action spaces that do not fall in the no-regret class." @default.
- W3120022075 created "2021-01-18" @default.
- W3120022075 creator A5013901541 @default.
- W3120022075 creator A5055691206 @default.
- W3120022075 date "2020-12-14" @default.
- W3120022075 modified "2023-10-16" @default.
- W3120022075 title "Multi-Agent Reinforcement Learning in Cournot Games" @default.
- W3120022075 cites W1963838585 @default.
- W3120022075 cites W1967250398 @default.
- W3120022075 cites W1972221945 @default.
- W3120022075 cites W1995734586 @default.
- W3120022075 cites W2026355589 @default.
- W3120022075 cites W2078338432 @default.
- W3120022075 cites W2081000975 @default.
- W3120022075 cites W2085963752 @default.
- W3120022075 cites W2133096155 @default.
- W3120022075 cites W2150865801 @default.
- W3120022075 cites W2169401877 @default.
- W3120022075 cites W2513180554 @default.
- W3120022075 cites W2915287126 @default.
- W3120022075 cites W2960876848 @default.
- W3120022075 cites W2962990479 @default.
- W3120022075 cites W3120022075 @default.
- W3120022075 cites W3122318673 @default.
- W3120022075 cites W3139232201 @default.
- W3120022075 cites W410025 @default.
- W3120022075 cites W4294576339 @default.
- W3120022075 doi "https://doi.org/10.1109/cdc42340.2020.9304089" @default.
- W3120022075 hasPublicationYear "2020" @default.
- W3120022075 type Work @default.
- W3120022075 sameAs 3120022075 @default.
- W3120022075 citedByCount "2" @default.
- W3120022075 countsByYear W31200220752020 @default.
- W3120022075 crossrefType "proceedings-article" @default.
- W3120022075 hasAuthorship W3120022075A5013901541 @default.
- W3120022075 hasAuthorship W3120022075A5055691206 @default.
- W3120022075 hasBestOaLocation W31200220752 @default.
- W3120022075 hasConcept C119857082 @default.
- W3120022075 hasConcept C121332964 @default.
- W3120022075 hasConcept C126255220 @default.
- W3120022075 hasConcept C144237770 @default.
- W3120022075 hasConcept C154945302 @default.
- W3120022075 hasConcept C162324750 @default.
- W3120022075 hasConcept C16520705 @default.
- W3120022075 hasConcept C177142836 @default.
- W3120022075 hasConcept C2777212361 @default.
- W3120022075 hasConcept C2777303404 @default.
- W3120022075 hasConcept C2780791683 @default.
- W3120022075 hasConcept C33923547 @default.
- W3120022075 hasConcept C41008148 @default.
- W3120022075 hasConcept C46814582 @default.
- W3120022075 hasConcept C50522688 @default.
- W3120022075 hasConcept C50817715 @default.
- W3120022075 hasConcept C62520636 @default.
- W3120022075 hasConcept C97541855 @default.
- W3120022075 hasConceptScore W3120022075C119857082 @default.
- W3120022075 hasConceptScore W3120022075C121332964 @default.
- W3120022075 hasConceptScore W3120022075C126255220 @default.
- W3120022075 hasConceptScore W3120022075C144237770 @default.
- W3120022075 hasConceptScore W3120022075C154945302 @default.
- W3120022075 hasConceptScore W3120022075C162324750 @default.
- W3120022075 hasConceptScore W3120022075C16520705 @default.
- W3120022075 hasConceptScore W3120022075C177142836 @default.
- W3120022075 hasConceptScore W3120022075C2777212361 @default.
- W3120022075 hasConceptScore W3120022075C2777303404 @default.
- W3120022075 hasConceptScore W3120022075C2780791683 @default.
- W3120022075 hasConceptScore W3120022075C33923547 @default.
- W3120022075 hasConceptScore W3120022075C41008148 @default.
- W3120022075 hasConceptScore W3120022075C46814582 @default.
- W3120022075 hasConceptScore W3120022075C50522688 @default.
- W3120022075 hasConceptScore W3120022075C50817715 @default.
- W3120022075 hasConceptScore W3120022075C62520636 @default.
- W3120022075 hasConceptScore W3120022075C97541855 @default.
- W3120022075 hasFunder F4320306076 @default.
- W3120022075 hasLocation W31200220751 @default.
- W3120022075 hasLocation W31200220752 @default.
- W3120022075 hasOpenAccess W3120022075 @default.
- W3120022075 hasPrimaryLocation W31200220751 @default.
- W3120022075 hasRelatedWork W1498243273 @default.
- W3120022075 hasRelatedWork W1522085547 @default.
- W3120022075 hasRelatedWork W1551422486 @default.
- W3120022075 hasRelatedWork W1553170689 @default.
- W3120022075 hasRelatedWork W1973594283 @default.
- W3120022075 hasRelatedWork W2044763837 @default.
- W3120022075 hasRelatedWork W2092048262 @default.
- W3120022075 hasRelatedWork W2488108158 @default.
- W3120022075 hasRelatedWork W4239167689 @default.
- W3120022075 hasRelatedWork W4253129534 @default.
- W3120022075 isParatext "false" @default.
- W3120022075 isRetracted "false" @default.
- W3120022075 magId "3120022075" @default.
- W3120022075 workType "article" @default.