A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
Explore this paper's citation graph
Summary
This paper generalizes the AlphaZero approach into a single AlphaZero algorithm that can achieve superhuman performance in many challenging games, and convincingly defeated a world champion program in the games of chess and shogi (Japanese chess), as well as Go.
- Type
- article
- Published
- 2018-12-07
- Cited by
- 4,187
- References
- 55
- Access
- Open access
- OpenAlex
- https://openalex.org/W2902907165
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:54457125
Keywords
Reinforcement learning, Reinforcement, Computer science, Artificial intelligence, Cognitive science
References
- Searching for solutions in games and artificial intelligence
- Encyclopedia of artificial intelligence, vols. 1 and 2 (2nd ed.)
- Behind Deep Blue
- Common Sense in Chess
- Giraffe: Using Deep Reinforcement Learning to Play Chess
- Uncertainty
- The Modern Chess Instructor
- The Legionella Kinase LegK2 Targets the ARP2/3 Complex To Inhibit Actin Nucleation on Phagosomes and Allow Bacterial Evasion of the Late Endocytic Pathway
- XXII. Programming a Computer for Playing Chess 1
- Multi-armed bandits with episode context
- Temporal difference learning applied to game playing and the results of application to Shogi
- Programming backgammon using self-teaching neural nets
- Temporal Difference Learning for Heuristic Search and Game Playing
- TD-Gammon, a Self-Teaching Backgammon Program, Achieves Master-Level Play
- A STRATEGIC METAGAME PLAYER FOR GENERAL CHESS‐LIKE GAMES
- Learning to Play Chess Using Temporal Differences
- General Game Playing: Overview of the AAAI Competition
- Bootstrapping from Game Tree Search
- On-line Policy Improvement using Monte-Carlo Search
- A Comparison of Prediction Accuracy, Complexity, and Training Time of Thirty-Three Old and New Classification Algorithms
Cited by
- A real-world test of artificial intelligence infiltration of a university examinations system: A “Turing Test” case study
- SAI a Sensible Artificial Intelligence that plays Go
- A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
- Learning and Acting in Peripersonal Space: Moving, Reaching, and Grasping
- TCEC13: The 13th top chess engine championship
- Mastering board games
- Theory of Cognitive Relativity: A Promising Paradigm for True AI
- Bayesian Optimization in AlphaGo
- Neural network based classification of crystal symmetries from x-ray diffraction patterns
- The Entropy of Artificial Intelligence and a Case Study of AlphaZero from Shannon's Perspective
- Large-Scale Optical Neural Networks based on Photoelectric Multiplication
- Pre-training with non-expert human demonstration for deep reinforcement learning
- Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Active Tasks
- Personal Universes: A Solution to the Multi-Agent Value Alignment Problem
- Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
- An estimation method for game complexity
- Reward Shaping via Meta-Learning
- Open-ended Learning in Symmetric Zero-sum Games
- The Hanabi Challenge: A New Frontier for AI Research
- Intuition, intelligence, data compression
Related papers
- Physician-Friendly Machine Learning: A Case Study with Cardiovascular Disease Risk Prediction
- Breakdown of Machine Learning Algorithms
- Application of Machine Learning in Animal Disease Analysis and Prediction
- Machine Learning Techniques for the Management of Diseases: A Paper Review
- Artificial Intelligence, Machine Learning, and Medicine: A Little Background Goes a Long Way Toward Understanding.
- A Comprehensive Review of Various Machine Learning Techniques
- Machine Learning and Deep Learning applications-a vision using the SPSS Method
- Machine Learning and Deep Learning for Maize Leaf Disease Classification: A Review
- Improving Clinical Prediction of Later Occurrence of Breast Cancer Metastasis Using Deep Learning and Machine Learning with Grid Search