Google AI algorithm masters ancient game of Go

  title={Google AI algorithm masters ancient game of Go},
  author={Elizabeth Gibney},
  • E. Gibney
  • Published 28 January 2016
  • Computer Science, Medicine
  • Nature
STRATEGY Chess is less complex than Go, but it still has too many possible configurations to solve by brute force alone. Instead, programs cut down their searches by looking a few turns ahead and judging which player would have the upper hand. In Go, recognizing winning and losing positions is much harder: stones have equal values and can have subtle impacts far across the board. To interpret Go boards and to learn the best possible moves, the AlphaGo program applied deep learning in neural… Expand
AlphaGo, Deep Learning, and the Future of the Human Microscopist.
In March of last year, Google’s artificial intelligence (AI) computer program AlphaGo beat the best Go player in the world, 18-time champion Lee Se-dol, in a tournament, winning 4 of 5 games. Expand
Very simple statistical evidence that AlphaGo has exceeded human limits in playing GO game
By looking at the statistical distribution of the distance in which the Go stones are laid in succession, a clear trace is found that Alphago has surpassed human abilities. Expand
Can Reinforcement Learning Be Applied to Surgery?
Investigating whether reinforcement learning could be used in sur­ gery in the future by setting rules, such as appropriate rewards and playable areas, in simulated tasks proposed proposes the combination of reinforcement learning and surgery. Expand
A New AI Open Problem: WUGU Chess
  • Chunxiao Ren, Yuxiao Wu
  • Computer Science
  • 2019 Eleventh International Conference on Advanced Computational Intelligence (ICACI)
  • 2019
This paper introduces a traditional chess game, WUGU chess, which is popular in Weifang area of Shandong Province, P.R. China, and introduces it as a new artificial intelligence (AI) open problem. Expand
Using Go in teaching the theory of computation
Some exercises developed during research on Go which were then used when teaching this subject at Monash University, based on One-Dimensional Go, which uses a path graph as its board are given. Expand
Improvements to Increase the Efficiency of the AlphaZero Algorithm: A Case Study in the Game 'Connect 4'
This paper proposes and investigates three modifications that model the self-learning phase as an evolutionary process, study the game process as a tree and use network-internal features as auxiliary targets to reduce the required computation resources. Expand
Computers Play Chess, Computers Play Go…Humans Play Dungeons & Dragons
The authors pose a true challenge for the next decade: attacking human-oriented games such as Dungeons & Dragons. Expand
Optimal strategies in the Fighting Fantasy gaming system: influencing stochastic dynamics by gambling with limited resource
This work uses stochastic analysis and simulation with dynamic programming to characterise the dynamical behaviour of the Fighting Fantasy system in the absence and presence of gambling policy, and derives a simple expression for the victory probability without luck-based strategy. Expand
Special issue on distributed computing and artificial intelligence
Research on distributed computing and artificial intelligence (DCAI) has matured during the last decade and many effective applications are now deployed, performing an increasingly important role in modern computer science, including the two most hyped technologies: Internet of Things and Big Data. Expand
Floyd-Warshall Reinforcement Learning Learning from Past Experiences to Reach New Goals
This work improves upon the limitations of model-free RL in multi-goal domains by adapting the Floyd-Warshall algorithm for RL and calling it FWRL, which learns a goal-conditioned action-value function by constraining the value of the optimal path between any two states to be greater than or equal to thevalue of paths via intermediary states. Expand


Mastering the game of Go with deep neural networks and tree search
Using this search algorithm, the program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0.5, the first time that a computer program has defeated a human professional player in the full-sized game of Go. Expand
Checkers Is Solved
This paper announces that checkers is now solved: Perfect play by both sides leads to a draw. Expand
Human-level control through deep reinforcement learning
This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks. Expand
  • R. Rosenfeld
  • Medicine
  • Otolaryngology--head and neck surgery : official journal of American Academy of Otolaryngology-Head and Neck Surgery
  • 2009
I am writing with a simple plea to balance the voluminous articles about treatment in your journal with a modicum of information about nature and caring effects to rekindle the perception of physicians as healers, not only treaters, who relish the gifts of nature, and foster the humanistic aspect of medicine that has thrived for millennia. Expand
Science today studies phenomena lasting less than 10−21 s and phenomena which occurred more than 13 billion years ago; science also studies phenomena occurring over distances greater than 1028 cm andExpand