Training Musculoskeletal Arm Play Taichi with Deep Reinforcement Learning.
Haoran XuXiang MaLeiyang XuQiang WangPublished in: I2MTC (2020)
Keyphrases
- reinforcement learning
- supervised learning
- training algorithm
- state space
- training phase
- deep architectures
- multi agent reinforcement learning
- reinforcement learning algorithms
- online learning
- game playing
- test set
- function approximation
- back propagation
- deep learning
- model free
- optimal control
- data sets
- training samples
- semi supervised
- training set
- multi agent
- knowledge base
- learning algorithm
- genetic algorithm