A Self-adaptive LSAC-PID Approach based on Lyapunov Reward Shaping for Mobile Robots.
Xinyi YuSiyu XuYuehai FanLinlin OuPublished in: CoRR (2021)
Keyphrases
- mobile robot
- reward shaping
- fuzzy pid control
- control scheme
- reinforcement learning
- pid controller
- complex domains
- control law
- control algorithm
- closed loop
- control method
- reinforcement learning algorithms
- control parameters
- path planning
- control system
- autonomous robots
- agent learns
- dynamic environments
- dynamical systems
- sufficient conditions
- state space
- markov decision problems
- control strategy
- fuzzy controller
- domain theory
- linear programming
- fuzzy systems
- search space
- multi agent