Corpus ID: 63349990

Programming a Hearthstone agent using Monte Carlo Tree Search

@inproceedings{Andersson2016ProgrammingAH,
  title={Programming a Hearthstone agent using Monte Carlo Tree Search},
  author={Markus Heikki Andersson and H{\aa}kon Helgesen Hesselberg},
  year={2016}
}
This thesis describes the effort of adapting Monte Carlo Tree Search (MCTS) to the game of Hearthstone, a card game with hidden information and stochastic elements. The focus is on discovering the suitability of MCTS for this environment, as well as which domainspecific adaptations are needed. An MCTS agent is developed for a Hearthstone simulator, which is used to conduct experiments to measure the agent’s performance both against human and computer players. The implementation includes… Expand
3 Citations
Monte Carlo tree search experiments in hearthstone
  • 23
  • PDF
Improving Hearthstone AI by Combining MCTS and Supervised Learning Algorithms
  • 29
  • PDF
Analysis of Card Collection Game ‘Hearthstone’*

References

SHOWING 1-10 OF 47 REFERENCES
Information Set Monte Carlo Tree Search
  • 113
  • PDF
Monte Carlo Tree Search for games with hidden information and uncertainty
  • 14
  • PDF
GIB: Imperfect Information in a Computationally Challenging Game
  • 181
  • PDF
A Survey of Monte Carlo Tree Search Methods
  • 1,773
  • Highly Influential
  • PDF
A Model of Two-Player Evaluation Functions
  • 14
On-line Policy Improvement using Monte-Carlo Search
  • 223
  • PDF
Mastering the game of Go with deep neural networks and tree search
  • 8,450
  • PDF
Monte-Carlo tree search and rapid action value estimation in computer Go
  • 283
  • PDF
Multi-armed Bandit Algorithms and Empirical Evaluation
  • 416
  • PDF
...
1
2
3
4
5
...