University of Sussex
Browse

File(s) not publicly available

The Potential of Reinforcement Learning for Live Musical Agents

presentation
posted on 2023-06-08, 06:23 authored by Nick Collins
Reinforcement learning has great potential applicability in computer music, particularly for interactive scenarios and the production of effective control policies for systems. This paper considers in particular the case of interactive music systems, where a software agent can be trained online during a rehearsal session with a musician. A small-scale system is described which uses the Sarsa(?) algorithm to update state-action values to determine a policy for output behaviours over a modest feature space. It is hoped that issues arising can be discussed fruitfully in a workshop context.

History

Publication status

  • Published

Presentation Type

  • paper

Event name

International Workshop on Machine Learning and Music 2008

Event location

Helsinki, Finland

Event type

conference

Department affiliated with

  • Informatics Publications

Full text available

  • No

Peer reviewed?

  • Yes

Legacy Posted Date

2012-02-06

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC