Matches in SemOpenAlex for { <https://semopenalex.org/work/W4282919292> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4282919292 abstract "This work studies an algorithm, which we call magnetic mirror descent, that is inspired by mirror descent and the non-Euclidean proximal gradient algorithm. Our contribution is demonstrating the virtues of magnetic mirror descent as both an equilibrium solver and as an approach to reinforcement learning in two-player zero-sum games. These virtues include: 1) Being the first quantal response equilibria solver to achieve linear convergence for extensive-form games with first order feedback; 2) Being the first standard reinforcement learning algorithm to achieve empirically competitive results with CFR in tabular settings; 3) Achieving favorable performance in 3x3 Dark Hex and Phantom Tic-Tac-Toe as a self-play deep reinforcement learning algorithm." @default.
- W4282919292 created "2022-06-16" @default.
- W4282919292 creator A5000720870 @default.
- W4282919292 creator A5006744201 @default.
- W4282919292 creator A5049659586 @default.
- W4282919292 creator A5059261578 @default.
- W4282919292 creator A5062059792 @default.
- W4282919292 creator A5075390126 @default.
- W4282919292 creator A5083207349 @default.
- W4282919292 creator A5088076429 @default.
- W4282919292 date "2022-06-12" @default.
- W4282919292 modified "2023-09-23" @default.
- W4282919292 title "A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games" @default.
- W4282919292 doi "https://doi.org/10.48550/arxiv.2206.05825" @default.
- W4282919292 hasPublicationYear "2022" @default.
- W4282919292 type Work @default.
- W4282919292 citedByCount "0" @default.
- W4282919292 crossrefType "posted-content" @default.
- W4282919292 hasAuthorship W4282919292A5000720870 @default.
- W4282919292 hasAuthorship W4282919292A5006744201 @default.
- W4282919292 hasAuthorship W4282919292A5049659586 @default.
- W4282919292 hasAuthorship W4282919292A5059261578 @default.
- W4282919292 hasAuthorship W4282919292A5062059792 @default.
- W4282919292 hasAuthorship W4282919292A5075390126 @default.
- W4282919292 hasAuthorship W4282919292A5083207349 @default.
- W4282919292 hasAuthorship W4282919292A5088076429 @default.
- W4282919292 hasBestOaLocation W42829192921 @default.
- W4282919292 hasConcept C11413529 @default.
- W4282919292 hasConcept C121332964 @default.
- W4282919292 hasConcept C126255220 @default.
- W4282919292 hasConcept C129782007 @default.
- W4282919292 hasConcept C136356330 @default.
- W4282919292 hasConcept C138885662 @default.
- W4282919292 hasConcept C145071142 @default.
- W4282919292 hasConcept C153258448 @default.
- W4282919292 hasConcept C153294291 @default.
- W4282919292 hasConcept C154945302 @default.
- W4282919292 hasConcept C15744967 @default.
- W4282919292 hasConcept C162324750 @default.
- W4282919292 hasConcept C2524010 @default.
- W4282919292 hasConcept C2776637919 @default.
- W4282919292 hasConcept C2777303404 @default.
- W4282919292 hasConcept C2778770139 @default.
- W4282919292 hasConcept C2780813799 @default.
- W4282919292 hasConcept C33923547 @default.
- W4282919292 hasConcept C41008148 @default.
- W4282919292 hasConcept C41895202 @default.
- W4282919292 hasConcept C46814582 @default.
- W4282919292 hasConcept C50522688 @default.
- W4282919292 hasConcept C50644808 @default.
- W4282919292 hasConcept C67203356 @default.
- W4282919292 hasConcept C77805123 @default.
- W4282919292 hasConcept C97541855 @default.
- W4282919292 hasConceptScore W4282919292C11413529 @default.
- W4282919292 hasConceptScore W4282919292C121332964 @default.
- W4282919292 hasConceptScore W4282919292C126255220 @default.
- W4282919292 hasConceptScore W4282919292C129782007 @default.
- W4282919292 hasConceptScore W4282919292C136356330 @default.
- W4282919292 hasConceptScore W4282919292C138885662 @default.
- W4282919292 hasConceptScore W4282919292C145071142 @default.
- W4282919292 hasConceptScore W4282919292C153258448 @default.
- W4282919292 hasConceptScore W4282919292C153294291 @default.
- W4282919292 hasConceptScore W4282919292C154945302 @default.
- W4282919292 hasConceptScore W4282919292C15744967 @default.
- W4282919292 hasConceptScore W4282919292C162324750 @default.
- W4282919292 hasConceptScore W4282919292C2524010 @default.
- W4282919292 hasConceptScore W4282919292C2776637919 @default.
- W4282919292 hasConceptScore W4282919292C2777303404 @default.
- W4282919292 hasConceptScore W4282919292C2778770139 @default.
- W4282919292 hasConceptScore W4282919292C2780813799 @default.
- W4282919292 hasConceptScore W4282919292C33923547 @default.
- W4282919292 hasConceptScore W4282919292C41008148 @default.
- W4282919292 hasConceptScore W4282919292C41895202 @default.
- W4282919292 hasConceptScore W4282919292C46814582 @default.
- W4282919292 hasConceptScore W4282919292C50522688 @default.
- W4282919292 hasConceptScore W4282919292C50644808 @default.
- W4282919292 hasConceptScore W4282919292C67203356 @default.
- W4282919292 hasConceptScore W4282919292C77805123 @default.
- W4282919292 hasConceptScore W4282919292C97541855 @default.
- W4282919292 hasLocation W42829192921 @default.
- W4282919292 hasOpenAccess W4282919292 @default.
- W4282919292 hasPrimaryLocation W42829192921 @default.
- W4282919292 hasRelatedWork W1980008589 @default.
- W4282919292 hasRelatedWork W2955291419 @default.
- W4282919292 hasRelatedWork W3127950324 @default.
- W4282919292 hasRelatedWork W3203238138 @default.
- W4282919292 hasRelatedWork W4281260729 @default.
- W4282919292 hasRelatedWork W4282919292 @default.
- W4282919292 hasRelatedWork W4319166651 @default.
- W4282919292 hasRelatedWork W4361253176 @default.
- W4282919292 hasRelatedWork W3173556592 @default.
- W4282919292 hasRelatedWork W4280542587 @default.
- W4282919292 isParatext "false" @default.
- W4282919292 isRetracted "false" @default.
- W4282919292 workType "article" @default.