Multi-Constraint Deep Reinforcement Learning for Smooth Action Control.
Guangyuan ZouYing HeF. Richard YuLongquan ChenWeike PanZhong MingPublished in: IJCAI (2022)
Keyphrases
- reinforcement learning
- action selection
- control problems
- optimal control
- partially observable domains
- control policy
- robot control
- control strategy
- action space
- machine learning
- function approximation
- mobile robot
- model free
- dynamic programming
- reward shaping
- control policies
- learning algorithm
- reinforcement learning algorithms
- robotic control
- control system
- state space
- data acquisition
- dynamic environments