Hierarchical Gait Generation for Modular Robots Using Deep Reinforcement Learning.
Jiayu WangChuxiong HuYu ZhuPublished in: ICM (2021)
Keyphrases
- reinforcement learning
- modular robots
- learning agents
- function approximation
- state space
- learning agent
- reinforcement learning algorithms
- markov decision processes
- learning algorithm
- robot behavior
- changing environment
- learning process
- domain knowledge
- optimal policy
- learning strategies
- temporal difference
- learning capabilities
- expert systems