Relaxation "sweet spot" exploration in pantophonic musical soundscape using reinforcement learning.
Isuru JayarathneMichael CohenMichael FrishkopfGregory MulykPublished in: IUI Companion (2019)
Keyphrases
- sweet spot
- reinforcement learning
- active exploration
- exploration strategy
- exploration exploitation
- action selection
- model based reinforcement learning
- exploration exploitation tradeoff
- function approximation
- reinforcement learning algorithms
- multi agent
- state space
- machine learning
- autonomous learning
- temporal difference learning
- model free
- genre classification
- multi agent reinforcement learning
- optimal policy
- learning process
- balancing exploration and exploitation
- objective function
- control policy
- lagrangian relaxation
- probabilistic relaxation
- temporal difference
- lower bound