Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory.
Siyao LiWeijiang YuTianpei GuChunze LinQuan WangChen QianChen Change LoyZiwei LiuPublished in: CoRR (2022)
Keyphrases
- actor critic
- reinforcement learning
- policy gradient
- neuro fuzzy
- function approximation
- optimal control
- evolutionary algorithm
- humanoid robot
- temporal difference
- reinforcement learning algorithms
- gradient method
- approximate dynamic programming
- multi agent
- artificial neural networks
- markov decision processes
- average reward