Stable Reinforcement Learning for Optimal Frequency Control: A Distributed Averaging-Based Integral Approach.
Yan JiangWenqi CuiBaosen ZhangJorge CortésPublished in: CoRR (2022)
Keyphrases
- optimal control
- reinforcement learning
- control policy
- control problems
- cooperative multi agent systems
- dynamic programming
- robot control
- multi agent
- distributed control
- distributed systems
- multi agent reinforcement learning
- control system
- control policies
- function approximation
- markov decision processes
- mobile agents
- control strategy
- master slave
- action selection
- state space
- locally optimal
- genetic algorithm
- optimal solution
- cooperative
- closed form
- average cost
- reinforcement learning algorithms
- adaptive control
- distributed environment
- optimal policy
- peer to peer