Adversarial Hierarchical-Task Network Planning for Complex Real-Time Games

@inproceedings{Ontan2015AdversarialHN,
  title={Adversarial Hierarchical-Task Network Planning for Complex Real-Time Games},
  author={Santiago Onta{\~n}{\'o}n and Michael Buro},
  booktitle={IJCAI},
  year={2015}
}
Real-time strategy (RTS) games are hard from an AI point of view because they have enormous state spaces, combinatorial branching factors, allow simultaneous and durative actions, and players have very little time to choose actions. For these reasons, standard game tree search methods such as alphabeta search or Monte Carlo Tree Search (MCTS) are not sufficient by themselves to handle these games. This paper presents an alternative approach called Adversarial Hierarchical Task Network (AHTN… CONTINUE READING
Highly Cited
This paper has 29 citations. REVIEW CITATIONS
22 Citations
27 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 22 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 27 references

In Proceedings of ECML 2006

  • Levente Kocsis, Csaba Szepesvri. Bandit based Monte Carlo planning
  • pages 282–293. Springer,
  • 2006
Highly Influential
4 Excerpts

Antonı́n Komenda

  • Alexander Shleyfman
  • and Carmel Domshlak. On combinatorial actions and…
  • 2014
Highly Influential
4 Excerpts

A Survey of Real-Time Strategy Game AI Research and Competition in StarCraft

  • Ontanón et al, 2013 Santiago Ontanón, +4 authors Mike Preuss
  • IEEE Transactions on Computational Intelligence…
  • 2013

In Computational Intelligence in Games (CIG)

  • David Churchill, Michael Buro. Portfolio greedy search, simulation for largescale combat in StarCraft
  • 2013 IEEE Conference on, pages 1–8. IEEE,
  • 2013
1 Excerpt

A survey of Monte Carlo tree search methods

  • Browne et al, 2012 C.B. Browne, +8 authors S. Colton
  • Computational Intelligence and AI in Games,
  • 2012

Similar Papers

Loading similar papers…