Enhancements for real-time Monte-Carlo Tree Search in General Video Game Playing

@article{Soemers2016EnhancementsFR,
  title={Enhancements for real-time Monte-Carlo Tree Search in General Video Game Playing},
  author={Dennis J. N. J. Soemers and Chiara F. Sironi and Torsten Schuster and Mark H. M. Winands},
  journal={2016 IEEE Conference on Computational Intelligence and Games (CIG)},
  year={2016},
  pages={1-8}
}
General Video Game Playing (GVGP) is a field of Artificial Intelligence where agents play a variety of real-time video games that are unknown in advance. This limits the use of domain-specific heuristics. Monte-Carlo Tree Search (MCTS) is a search technique for game playing that does not rely on domain-specific knowledge. This paper discusses eight enhancements for MCTS in GVGP; Progressive History, N-Gram Selection Technique, Tree Reuse, Breadth-First Tree Initialization, Loss Avoidance… CONTINUE READING
Highly Cited
This paper has 24 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 14 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 31 references

Analysing and Improving the Knowledge-based Fast Evolutionary MCTS Algorithm

  • J. van Eeden
  • Master’s thesis, Utrecht University, Utrecht, the…
  • 2015
1 Excerpt

MCTS Based Agent for General Video Games

  • T. Schuster
  • Master’s thesis, Department of Knowledge…
  • 2015
1 Excerpt

Similar Papers

Loading similar papers…