Anticipatory Model of Musical Style Imitation Using Collaborative and Competitive Reinforcement Learning

Authors:
Arshia Cont;Shlomo Dubnov;Gérard Assayag
Affiliations:
Ircam - Centre Pompidou - UMR CNRS 9912, Paris, and Center for Research in Computing and the Arts, UCSD, CA,;Center for Research in Computing and the Arts, UCSD, CA,;Ircam - Centre Pompidou - UMR CNRS 9912, Paris,
Venue:
Anticipatory Behavior in Adaptive Learning Systems
Year:
2007

Citing 10
Cited 3

Prioritized Sweeping: Reinforcement Learning with Less Data and Less Time

Machine Learning
The power of amnesia: learning probabilistic automata with variable memory length

Machine Learning - Special issue on COLT '94
Mixed Memory Markov Models: Decomposing Complex Stochastic Processes as Mixtures of Simpler Ones

Machine Learning
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Factor Oracle: A New Structure for Pattern Matching

SOFSEM '99 Proceedings of the 26th Conference on Current Trends in Theory and Practice of Informatics on Theory and Practice of Informatics
Using Factor Oracles for Machine Improvisation

Soft Computing - A Fusion of Foundations, Methodologies and Applications
Spectral Anticipations

Computer Music Journal
Using Machine-Learning Methods for Musical Style Modeling

Computer
Methods for combining statistical models of music

CMMR'04 Proceedings of the Second international conference on Computer Music Modeling and Retrieval
Linear time universal coding and time reversal of tree sources via FSM closure

IEEE Transactions on Information Theory

Anticipations, Brains, Individual and Social Behavior: An Introduction to Anticipatory Systems

Anticipatory Behavior in Adaptive Learning Systems
Markov constraints: steerable generation of Markov sequences

Constraints
Finite-length Markov processes with constraints

IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume One

Quantified Score

Hi-index	0.00

Visualization

Abstract

The role of expectationin listening and composing music has drawn much attention in music cognition since about half a century ago. In this paper, we provide a first attempt to model some aspects of musical expectation specifically pertained to short-time and working memories, in an anticipatory framework. In our proposition anticipationis the mental realization of possible predicted actions and their effect on the perception of the world at an instant in time. We demonstrate the model in applications to automatic improvisation and style imitation. The proposed model, based on cognitive foundations of musical expectation, is an active model using reinforcement learning techniques with multiple agents that learn competitively and in collaboration. We show that compared to similar models, this anticipatory framework needs little training data and demonstrates complex musical behavior such as long-term planning and formal shapes as a result of the anticipatory architecture. We provide sample results and discuss further research.