Building behavior trees from observations in real-time strategy games
Authors:
- 1 September 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 33, 1-7
Abstract
This paper presents a novel use of motif-finding techniques from computational biology to find recurring action sequences across many observations of expert humans carrying out a complex task. Information about recurring action sequences is used to produce a behavior tree without any additional domain information besides a simple similarity metric - no action models or reward functions are provided. This technique is applied to produce a behavior tree for strategic-level actions in the real-time strategy game StarCraft. The behavior tree was able to represent and summarise a large amount of information from the expert behavior examples much more compactly. The method could still be improved by discovering reactive actions present in the expert behavior and encoding these in the behavior tree.Keywords
This publication has 16 references indexed in Scilit:
- A Review of Real‐Time Strategy Game AIAI Magazine, 2014
- Integrating Case-Based Reasoning with Reinforcement Learning for Real-Time Strategy Game Micromanagement2014
- Real‐Time Strategy Game CompetitionsAI Magazine, 2012
- Combining Expert Knowledge and Learning from Demonstration in Real-Time Strategy Games2011
- Evolving Behaviour Trees for the Commercial Game DEFCON2010
- Discovering Sequence Motifs with Arbitrary Insertions and DeletionsPLOS Computational Biology, 2008
- Learning action models from plan examples using weighted MAX-SATArtificial Intelligence, 2007
- LEARNING PRECONDITIONS FOR PLANNING FROM PLAN TRACES AND HTN STRUCTUREComputational Intelligence, 2005
- Learning by Observation and Practice: An Incremental Approach for Planning Operator Acquisition1995
- Strips: A new approach to the application of theorem proving to problem solvingArtificial Intelligence, 1971