Related papers: Reinforcement Learning Jazz Improvisation: When Mu…

This paper presents a deep reinforcement learning algorithm for online accompaniment generation, with potential for real-time interactive human-machine duet improvisation. Different from offline music generation and harmonization, online…

Most applications of generative AI involve a sequential interaction in which a person inputs a prompt and waits for a response, and where reaction time and adaptivity are not important factors. In contrast, live jamming is a collaborative…

We propose a method for the problem of real time chord accompaniment of improvised music. Our implementation can learn an underlying structure of the musical performance and predict next chord. The system uses Hidden Markov Model to find…

In common-interest stochastic games all players receive an identical payoff. Players participating in such games must learn to coordinate with each other in order to receive the highest-possible value. A number of reinforcement learning…

Score following is the process of tracking a musical performance (audio) with respect to a known symbolic representation (a score). We start this paper by formulating score following as a multimodal Markov Decision Process, the mathematical…

Symbolic Music Alignment is the process of matching performed MIDI notes to corresponding score notes. In this paper, we introduce a reinforcement learning (RL)-based online symbolic music alignment technique. The RL agent - an…

Compositional generalization refers to correctly interpret novel combinations of known primitives, which remains a major challenge. Existing approaches often rely on supervised fine-tuning, which encourages models to imitate target outputs.…

We investigate a class of reinforcement learning dynamics where players adjust their strategies based on their actions' cumulative payoffs over time - specifically, by playing mixed strategies that maximize their expected cumulative payoff…

Solving a reinforcement learning problem typically involves correctly prespecifying the reward signal from which the algorithm learns. Here, we approach the problem of reward signal design by using an evolutionary approach to perform a…

We study the problem of learning control policies for complex tasks given by logical specifications. Recent approaches automatically generate a reward function from a given specification and use a suitable reinforcement learning algorithm…

State-of-the-art model-based reinforcement learning methods train policies on imagined rollouts. These rollouts are trajectories generated by a learned dynamics model and are scored by a learned reward model, but without querying the true…

In this paper, harmony search algorithm is applied to curriculum-based course timetabling. The implementation, specifically the process of improvisation consists of memory consideration, random consideration and pitch adjustment. In memory…

Jamming requires coordination, anticipation, and collaborative creativity between musicians. Current generative models of music produce expressive output but are not able to generate in an \emph{online} manner, meaning simultaneously with…

This paper studies two important signal processing aspects of equilibrium behavior in non-cooperative games arising in social networks, namely, reinforcement learning and detection of equilibrium play. The first part of the paper presents a…

We propose a new framework for imitation learning -- treating imitation as a two-player ranking-based game between a policy and a reward. In this game, the reward agent learns to satisfy pairwise performance rankings between behaviors,…

We propose a compositional approach to synthesize policies for networks of continuous-space stochastic control systems with unknown dynamics using model-free reinforcement learning (RL). The approach is based on implicitly abstracting each…

As generative models have risen in popularity, a domain that has risen alongside is generative models for music. Our study aims to compare the performance of a simple Markov chain model and a recurrent neural network (RNN) model, two…

We present the first reinforcement-learning model to self-improve its reward-modulated training implemented through a continuously improving "intuition" neural network. An agent was trained how to play the arcade video game Pong with two…

Recent advances in machine learning have paved the way for the development of musical and entertainment robots. However, human-robot cooperative instrument playing remains a challenge, particularly due to the intricate motor coordination…

A music mashup combines audio elements from two or more songs to create a new work. To reduce the time and effort required to make them, researchers have developed algorithms that predict the compatibility of audio elements. Prior work has…