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 1–25 of 62 papers

TitleStatusHype
Accelerating Self-Play Learning in GoCode2
Mastering Atari, Go, Chess and Shogi by Planning with a Learned ModelCode2
Are AlphaZero-like Agents Robust to Adversarial Perturbations?Code1
Planning in Stochastic Environments with a Learned ModelCode1
Active Reinforcement Learning for Robust Building ControlCode1
Move Evaluation in Go Using Deep Convolutional Neural NetworksCode1
Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning AlgorithmCode1
Hyper-Parameter Sweep on AlphaZero GeneralCode1
MoËT: Mixture of Expert Trees and its Application to Verifiable Reinforcement LearningCode1
Teaching Deep Convolutional Neural Networks to Play GoCode1
Visualizing MuZero ModelsCode1
Conservative Optimistic Policy Optimization via Multiple Importance SamplingCode0
The Computational Limits of Deep LearningCode0
Monte Carlo Tree Search with Boltzmann ExplorationCode0
Perceptual Similarity for Measuring Decision-Making Style and Policy Diversity in GamesCode0
FML-based Dynamic Assessment Agent for Human-Machine Cooperative System on Game of GoCode0
Better Computer Go Player with Neural Network and Long-term PredictionCode0
ELF OpenGo: An Analysis and Open Reimplementation of AlphaZeroCode0
Learning and Planning in Complex Action SpacesCode0
Derived metrics for the game of Go -- intrinsic network strength assessment and cheat-detectionCode0
Deep Reinforcement Learning for 5*5 Multiplayer Go—0
Deep Network Guided Proof Search—0
Human vs. Computer Go: Review and Prospect—0
Generative Adversarial Imagination for Sample Efficient Deep Reinforcement Learning—0
Comparing Knowledge-based Reinforcement Learning to Neural Networks in a Strategy Game—0
Show:102550
← PrevPage 1 of 3Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AlphaGo ZeroELO Rating5,185—Unverified