ITU

Learning a Behavioral Repertoire from Demonstrations

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

View graph of relations

Imitation Learning (IL) is a machine learning approach to learn a policy from a set of demonstrations. IL can be useful to kick-start learning before applying reinforcement learning (RL) but it can also be useful on its own, e.g. to learn to imitate human players in video games. Despite the success of systems that use IL and RL, how such systems can adapt in-between game rounds is a neglected area of study but an important aspect of many strategy games. In this paper, we present a new approach called Behavioral Repertoire Imitation Learning (BRIL) that learns a repertoire of behaviors from a set of demonstrations by augmenting the state-action pairs with behavioral descriptions. The outcome of this approach is a single neural network policy conditioned on a behavior description that can be precisely modulated. We apply this approach to train a policy on 7,777 human demonstrations for the build-order planning task in StarCraft II. Dimensionality reduction is applied to construct a low-dimensional behavioral space from a high-dimensional description of the army unit composition of each human replay. The results demonstrate that the learned policy can be effectively manipulated to express distinct behaviors. Additionally, by applying the UCB1 algorithm, the policy can adapt its behavior - in-between games - to reach a performance beyond that of the traditional IL baseline approach.
Original languageEnglish
Title of host publicationProceedings of the 2020 IEEE Conference on Games
Number of pages8
PublisherIEEE
Publication date2020
Pages383-390
DOIs
Publication statusPublished - 2020
EventIEEE Conference on Games 2020 -
Duration: 24 Aug 202027 Nov 2020
https://ieee-cog.org/2020/

Conference

ConferenceIEEE Conference on Games 2020
Periode24/08/202027/11/2020
Internetadresse

ID: 85520181