Share This Author
Portfolio greedy search and simulation for large-scale combat in starcraft
- David Churchill, M. Buro
- Computer ScienceIEEE Conference on Computational Inteligence in…
- 17 October 2013
This paper presents an efficient system for modelling abstract RTS combat called SparCraft, which can perform millions of unit actions per second and visualize them, and presents a modification of the UCT algorithm capable of performing search in games with simultaneous and durative actions.
Fast Heuristic Search for RTS Game Combat Scenarios
A fast search method — Alpha-Beta search for durative moves — that can defeat commonly used AI scripts in RTS game combat scenarios of up to 8 vs. 8 units running on a single core in under 5ms per search episode is presented.
Partial Pathfinding Using Map Abstraction and Refinement
This paper introduces Partial-Refinement A* (PRA*), which can fully interleave planning and acting through path abstraction and refinement, and demonstrates the etfectiveness of PRA* in the domain of real-time strategy (RTS) games.
From Simple Features to Sophisticated Evaluation Functions
- M. Buro
- Computer ScienceComputers and Games
- 11 November 1998
A practical framework for the semi-automatic construction of evaluation-functions for games based on a structured evaluation function representation is presented that is able to discover new features in a computationally feasible way.
Call for AI Research in RTS Games
- M. Buro
- Computer Science
This position paper discusses AI challenges in the area of real‐time strategy games and presents a research agenda aimed at improving AI performance in these popular multi‐ player computer games.
Build Order Optimization in StarCraft
This paper presents abstractions and heuristics that speed up the search for approximative solutions considerably in the game of StarCraft, and shows the efficacy of the method by comparing its real-time performance with that of professional StarCraft players.
Efficient Triangulation-Based Pathfinding
In this paper we present a method for abstracting an environment represented using constrained Delaunay triangulations in a way that significantly reduces pathfinding search effort, as well as better…
Improving heuristic mini-max search by supervised learning
- M. Buro
- Computer ScienceArtif. Intell.
- 24 January 2002
Combining Strategic Learning with Tactical Search in Real-Time Strategy Games
This is the first successful application of a convolutional network to play a full RTS game on standard game maps, as previous work has focused on sub-problems, such as combat, or on very small maps.
Adversarial Hierarchical-Task Network Planning for Complex Real-Time Games
This paper presents an alternative approach to adversarial Hierarchical Task Network planning that combines ideas from game tree search with HTN planning, and presents empirical results for the µRTS game, comparing it to other state of the art search algorithms for RTS games.