Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment.
Li SiyaoTianpei GuZhitao YangZhengyu LinZiwei LiuHenghui DingLei YangChen Change LoyPublished in: ICLR (2024)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- markov decision processes
- state space
- motion capture
- robotic control
- control problems
- model free
- optimal control
- optimal policy
- learning algorithm
- machine learning
- temporal difference
- multi agent
- dynamic programming
- action selection
- function approximators
- human movement
- learning problems
- neural network
- artificial neural networks
- information systems
- robot control
- action space
- reinforcement learning methods
- multi agent reinforcement learning
- policy search