Computer-Go am HPI

Ideensammlung zum Computer-Go-Seminar des HPI

ToDos

• Ausarbeitung der Gruppenaufteilung
  • verschiedene Themen der Gruppen?
  • konkurrierende Gruppen?
• Anforderungen an die Teilnehmer definieren
• Hardware-Anforderungen definieren
• Literatur zusammentragen
• Basic-Player evaluieren
• SVN organisieren
• Mailingliste einrichten
• Kooperation mit anderen Lehrstühlen klären

Eckpunkte

• 6 - 10 Teilnehmer

Literatur

(Auszug aus den Veröffentlichungen der letzten Jahre)

• Monte Carlo Tree Search
  • PHD: A CONTRIBUTION TO REINFORCEMENT LEARNING; APPLICATION TO COMPUTER-GO
  • PROGRESSIVE STRATEGIES FOR MONTE-CARLO TREE SEARCH
  • CROSS-ENTROPY FOR MONTE-CARLO TREE SEARCH
  • Combining Final Score with Winning Percentage by Sigmoid Function in Monte-Carlo Simulations
  • On the Laziness of Monte-Carlo Game Tree Search in Non-tight Situations
  • Transpositions and Move Groups in Monte Carlo Tree Search
  • Monte Carlo Temperature Discovery Search for Combinatorial Games
  • Parallel Monte-Carlo Tree Search with Simulation Servers
  • THE PARALLELIZATION OF MONTE-CARLO PLANNING
  • A Lock-free Multithreaded Monte-Carlo Tree Search Algorithm

• Other
  • PHD: AI techniques for the game of Go (2004)
  • Modelling Uncertainty in the Game of Go
  • Learning Position Evaluation for Go with Internal Symmetry Networks (Neuronale Netze)
  • Coevolving Partial Strategies for the Game of Go (Genetic algorithm) (lokale Kopie)
  • Lambda Depth-first Proof Number Search and its Application to Go
  • MSc Thesis: Learning Patterns in the Game of Go

Basicplayer

• Java
  • plug-and-go
  • Java-Bot by Don Dailey
• C++
  • fuego
• Go
  • Gongo

Links

• why programmers should play go