RL-Duet: Online Music Accompaniment Generation Using Deep Reinforcement Learning.
Nan JiangSheng JinZhiyao DuanChangshui ZhangPublished in: AAAI (2020)
Keyphrases
- reinforcement learning
- function approximation
- balancing exploration and exploitation
- model free
- control problems
- state space
- reinforcement learning algorithms
- optimal policy
- markov decision processes
- temporal difference
- pre recorded
- real time
- learning algorithm
- online learning
- dynamic programming
- temporal difference learning
- multi agent
- transfer learning
- machine learning
- policy evaluation
- rl algorithms
- reinforcement learning methods
- learning agents
- action selection
- continuous state
- approximate dynamic programming
- policy search
- optimal control
- learning problems
- markov decision process
- function approximators
- learned knowledge
- complex domains
- learning process
- learning classifier systems
- partially observable domains