Papers with Code 아카이브
Game of Go
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 1
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
MASTER: A Multi-Agent System with LLM Specialized MCTS
Perceptual Similarity for Measuring Decision-Making Style and Policy Diversity in Games
Deep Reinforcement Learning for 5*5 Multiplayer Go
Monte Carlo Tree Search with Boltzmann Exploration
Task Success is not Enough: Investigating the Use of Video-Language Models as Behavior Critics for Catching Undesirable Agent Behaviors
Active Reinforcement Learning for Robust Building Control
Explaining How a Neural Network Play the Go Game and Let People Learn
Vision Transformers for Computer Go
AlphaZero Gomoku
Are AlphaZero-like Agents Robust to Adversarial Perturbations?
The ProfessionAl Go annotation datasEt (PAGE)
The cost of passing -- using deep learning AIs to expand our understanding of the ancient game of Go
Score vs. Winrate in Score-Based Games: which Reward for Reinforcement Learning?
Spatial State-Action Features for General Games
Probabilistic DAG Search
Learning and Planning in Complex Action Spaces
Batch Monte Carlo Tree Search
Conservative Optimistic Policy Optimization via Multiple Importance Sampling
Visualizing MuZero Models
Derived metrics for the game of Go -- intrinsic network strength assessment and cheat-detection
Mobile Networks for Computer Go
The Computational Limits of Deep Learning
The Go Transformer: Natural Language Modeling for Game Play
Tackling Morpion Solitaire with AlphaZero-likeRanked Reward Reinforcement Learning
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Multi-step Greedy Reinforcement Learning Algorithms
Playing Go without Game Tree Search Using Convolutional Neural Networks
Designing Game of Theorems
MoËT: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learning
Building a Computer Mahjong Player via Deep Convolutional Neural Networks
Generative Adversarial Imagination for Sample Efficient Deep Reinforcement Learning
Hyper-Parameter Sweep on AlphaZero General
Accelerating Self-Play Learning in Go
ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero
A GFML-based Robot Agent for Human and Machine Cooperative Learning on Game of Go
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.