Efficient Behavior Learning by Utilizing Estimated State Value of Self and Teammates

Shimada, Kouki; Takahashi, Yasutake; Asada, Minoru

doi:10.1007/978-3-642-11876-0_31

Cited by 1 publication

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, for learning and recognition of events in an aircraft loading domain (Sridhar and Cohn 2010) and desktop activities (Behera, Cohn, and Hogg 2012), and for reinforcementlearning for robot navigation (Frommberger 2008). The problem of behaviour modelling in RoboCup Soccer, another simulated domain, has been tackled in a number of ways including reinforcement learning (Vieira, Adeodato, and Gon 2010;Jung and Polani 2012;Shimada, Takahashi, and Asada 2010;Molineaux, Aha, and Sukthankar 2008), and case-based reasoning (Ros, Llu, and Mantaras ;Floyd, Esfandiari, and Lam 2008). However in general, little work investigates the application of qualitative, relational representations to the problem of learning by observation.…”

Section: Related Workmentioning

confidence: 99%

Learning Micro-Management Skills in RTS Games by Imitating Experts

Young

Hawes

2021

AIIDE

View full text Add to dashboard Cite

We investigate the problem of learning the control of small groups of units in combat situations in Real Time Strategy (RTS) games. AI systems may acquire such skills by observing and learning from expert players, or other AI systems performing those tasks. However, access to training data may be limited, and representations based on metric information -- position, velocity, orientation etc. -- may be brittle, difficult for learning mechanisms to work with, and generalise poorly to new situations. In this work we apply \textit{qualitative spatial relations} to compress such continuous, metric state-spaces into symbolic states, and show that this makes the learning problem easier, and allows for more general models of behaviour. Models learnt from this representation are used to control situated agents, and imitate the observed behaviour of both synthetic (pre-programmed) agents, as well as the behaviour of human-controlled agents on a number of canonical micro-management tasks. We show how a Monte-Carlo method can be used to decompress qualitative data back in to quantitative data for practical use in our control system. We present our work applied to the popular RTS game Starcraft.

show abstract