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

Showing 2650 of 62 papers

TitleStatusHype
AlphaZero Gomoku0
A Popperian Falsification of Artificial Intelligence -- Lighthill Defended0
Bandit Algorithms for Tree Search0
Batch Monte Carlo Tree Search0
Building a Computer Mahjong Player via Deep Convolutional Neural Networks0
Can Machine Generate Traditional Chinese Poetry? A Feigenbaum Test0
Comparing Knowledge-based Reinforcement Learning to Neural Networks in a Strategy Game0
Deep Network Guided Proof Search0
Deep Reinforcement Learning for 5*5 Multiplayer Go0
Spatial State-Action Features for General Games0
Tackling Morpion Solitaire with AlphaZero-likeRanked Reward Reinforcement Learning0
Task Success is not Enough: Investigating the Use of Video-Language Models as Behavior Critics for Catching Undesirable Agent Behaviors0
The cost of passing -- using deep learning AIs to expand our understanding of the ancient game of Go0
The Go Transformer: Natural Language Modeling for Game Play0
The ProfessionAl Go annotation datasEt (PAGE)0
Towards Deep Symbolic Reinforcement Learning0
Vision Transformers for Computer Go0
What do we need to build explainable AI systems for the medical domain?0
MoET: Interpretable and Verifiable Reinforcement Learning via Mixture of Expert Trees0
Monte Carlo Tree Search with Sampled Information Relaxation Dual Bounds0
Multi-step Greedy Policies in Model-Free Deep Reinforcement Learning0
Multi-step Greedy Reinforcement Learning Algorithms0
Neurohex: A Deep Q-learning Hex Agent0
PFML-based Semantic BCI Agent for Game of Go Learning and Prediction0
Playing Go without Game Tree Search Using Convolutional Neural Networks0
Show:102550
← PrevPage 2 of 3Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AlphaGo ZeroELO Rating5,185Unverified