Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment.
Li SiyaoTianpei GuZhitao YangZhengyu LinZiwei LiuHenghui DingLei YangChen Change LoyPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- temporal difference
- state space
- reinforcement learning algorithms
- learning algorithm
- learning process
- optimal policy
- markov decision processes
- action selection
- model free
- reinforcement learning methods
- transfer learning
- learning agents
- robot control
- artificial intelligence
- machine learning
- direct policy search
- temporal difference learning
- policy search
- real time
- motion capture
- dynamic programming
- multi agent
- knowledge base
- e learning
- data mining