AlphaZero is a reinforcement learning agent for playing board games such as Go, chess, and shogi.

Source: Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

Latest Papers

PAPER DATE
Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets in Chess
Nenad TomaševUlrich PaquetDemis HassabisVladimir Kramnik
2020-09-09
Learning Personalized Models of Human Behavior in Chess
Reid McIlroy-YoungRussell WangSiddhartha SenJon KleinbergAshton Anderson
2020-08-23
Learning Compositional Neural Programs for Continuous Control
Thomas PierrotNicolas PerrinFeryal BehbahaniAlexandre LaterreOlivier SigaudKarim BeguirNando de Freitas
2020-07-27
Combining Deep Reinforcement Learning and Search for Imperfect-Information Games
Noam BrownAnton BakhtinAdam LererQucheng Gong
2020-07-27
Monte-Carlo Tree Search as Regularized Policy Optimization
Jean-Bastien GrillFlorent AltchéYunhao TangThomas HubertMichal ValkoIoannis AntonoglouRémi Munos
2020-07-24
Convex Regularization in Monte-Carlo Tree Search
Tuan DamCarlo D'EramoJan PetersJoni Pajarinen
2020-07-01
Aligning Superhuman AI and Human Behavior: Chess as a Model System
| Reid McIlroy-YoungSiddhartha SenJon KleinbergAshton Anderson
2020-06-02
Think Too Fast Nor Too Slow: The Computational Trade-off Between Planning And Reinforcement Learning
Thomas M. MoerlandAnna DeichlerSimone BaldiJoost BroekensCatholijn M. Jonker
2020-05-15
Neural Machine Translation with Monte-Carlo Tree Search
| Jerrod ParkerJerry Zikun Chen
2020-04-27
Warm-Start AlphaZero Self-Play Search Enhancements
Hui WangMike PreussAske Plaat
2020-04-26
Approximate exploitability: Learning a best response in large games
Finbarr TimbersEdward LockhartMarc LanctotMartin SchmidJulian SchrittwieserThomas HubertMichael Bowling
2020-04-20
Accelerating and Improving AlphaZero Using Population Based Training
Ti-Rong WuTing-Han WeiI-Chen Wu
2020-03-13
Learning to Resolve Alliance Dilemmas in Many-Player Zero-Sum Games
Edward HughesThomas W. AnthonyTom EcclesJoel Z. LeiboDavid BalduzziYoram Bachrach
2020-02-27
Polygames: Improved Zero Learning
Tristan CazenaveYen-Chi ChenGuan-Wei ChenShi-Yu ChenXian-Dong ChiuJulien DehosMaria ElsaQucheng GongHengyuan HuVasil KhalidovCheng-Ling LiHsin-I LinYu-Jin LinXavier MartinetVegard MellaJeremy RapinBaptiste RoziereGabriel SynnaeveFabien TeytaudOlivier TeytaudShi-Cheng YeYi-Jun YeShi-Jim YenSergey Zagoruyko
2020-01-27
Three-Head Neural Network Architecture for AlphaZero Learning
Anonymous
2020-01-01
Self-Play Learning Without a Reward Metric
Dan SchmidtNick MoranJonathan S. RosenfeldJonathan RosenthalJonathan Yedidia
2019-12-16
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
| Julian SchrittwieserIoannis AntonoglouThomas HubertKaren SimonyanLaurent SifreSimon SchmittArthur GuezEdward LockhartDemis HassabisThore GraepelTimothy LillicrapDavid Silver
2019-11-19
Multiplayer AlphaZero
| Nick PetosaTucker Balch
2019-10-29
Exploring the Performance of Deep Residual Networks in Crazyhouse Chess
| Sun-Yu Gordon Chi
2019-08-25
Performing Deep Recurrent Double Q-Learning for Atari Games
Felipe Moreno-Vera
2019-08-16
Multiple Policy Value Monte Carlo Tree Search
Li-Cheng LanWei LiTing-Han WeiI-Chen Wu
2019-05-31
Learning Compositional Neural Programs with Recursive Tree Search and Planning
Thomas PierrotGuillaume LignerScott ReedOlivier SigaudNicolas PerrinAlexandre LaterreDavid KasKarim BeguirNando de Freitas
2019-05-30
Deep Policies for Width-Based Planning in Pixel Domains
| Miquel JunyentAnders JonssonVicenç Gómez
2019-04-12
Improved Reinforcement Learning with Curriculum
Joseph WestFrederic MaireCameron BrowneSimon Denman
2019-03-29
Hyper-Parameter Sweep on AlphaZero General
| Hui WangMichael EmmerichMike PreussAske Plaat
2019-03-19
α-Rank: Multi-Agent Evaluation by Evolution
Shayegan OmidshafieiChristos PapadimitriouGeorgios PiliourasKarl TuylsMark RowlandJean-Baptiste LespiauWojciech M. CzarneckiMarc LanctotJulien PerolatRemi Munos
2019-03-04
Accelerating Self-Play Learning in Go
| David J. Wu
2019-02-27
ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero
| Yuandong TianJerry MaQucheng GongShubho SenguptaZhuoyuan ChenJames PinkertonC. Lawrence Zitnick
2019-02-12
The Entropy of Artificial Intelligence and a Case Study of AlphaZero from Shannon's Perspective
Bo ZhangBin ChenJin-lin Peng
2018-12-14
Assessing the Potential of Classical Q-learning in General Game Playing
| Hui WangMichael EmmerichAske Plaat
2018-10-14
ExIt-OOS: Towards Learning from Planning in Imperfect Information Games
| Andy KitchenMichela Benedetti
2018-08-30
Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization
| Alexandre LaterreYunguan FuMohamed Khalil JabriAlain-Sam CohenDavid KasKarl HajjarTorbjorn S. DahlAmine KerkeniKarim Beguir
2018-07-04
Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
| David SilverThomas HubertJulian SchrittwieserIoannis AntonoglouMatthew LaiArthur GuezMarc LanctotLaurent SifreDharshan KumaranThore GraepelTimothy LillicrapKaren SimonyanDemis Hassabis
2017-12-05

Tasks

TASK PAPERS SHARE
Game of Go 5 19.23%
Atari Games 4 15.38%
Decision Making 4 15.38%
Board Games 4 15.38%
Game of Chess 2 7.69%
Game of Shogi 2 7.69%
Machine Translation 1 3.85%
Multi-agent Reinforcement Learning 1 3.85%
Mathematical Proofs 1 3.85%

Components

COMPONENT TYPE
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories