SOTAVerified

Game of Go

Go is an abstract strategy board game for two players, in which the aim is to surround more territory than the opponent. The task is to train an agent to play the game and be superior to other players.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 62 papers

TitleStatusHype
Accelerating Self-Play Learning in GoCode2
Mastering Atari, Go, Chess and Shogi by Planning with a Learned ModelCode2
Planning in Stochastic Environments with a Learned ModelCode1
MoËT: Mixture of Expert Trees and its Application to Verifiable Reinforcement LearningCode1
Are AlphaZero-like Agents Robust to Adversarial Perturbations?Code1
Active Reinforcement Learning for Robust Building ControlCode1
Hyper-Parameter Sweep on AlphaZero GeneralCode1
Move Evaluation in Go Using Deep Convolutional Neural NetworksCode1
Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning AlgorithmCode1
Teaching Deep Convolutional Neural Networks to Play GoCode1
Show:102550
← PrevPage 1 of 7Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AlphaGo ZeroELO Rating5,185—Unverified