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 31–40 of 62 papers

TitleStatusHype
The Computational Limits of Deep LearningCode0
The Go Transformer: Natural Language Modeling for Game Play—0
Tackling Morpion Solitaire with AlphaZero-likeRanked Reward Reinforcement Learning—0
Multi-step Greedy Reinforcement Learning Algorithms—0
Multi-step Greedy Policies in Model-Free Deep Reinforcement Learning—0
MoET: Interpretable and Verifiable Reinforcement Learning via Mixture of Expert Trees—0
Playing Go without Game Tree Search Using Convolutional Neural Networks—0
Designing Game of Theorems—0
Building a Computer Mahjong Player via Deep Convolutional Neural Networks—0
Generative Adversarial Imagination for Sample Efficient Deep Reinforcement Learning—0
Show:102550
← PrevPage 4 of 7Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AlphaGo ZeroELO Rating5,185—Unverified