Continuous control of structural vibrations using hybrid deep reinforcement learning policy.
Jagajyoti PandaMudit ChopraVasant MatsagarSouvik ChakrabortyPublished in: Expert Syst. Appl. (2024)
Keyphrases
- reinforcement learning
- control policy
- action space
- control problems
- control policies
- optimal policy
- action selection
- continuous state spaces
- optimal control
- state space
- continuous state
- receding horizon
- policy search
- markov decision process
- adaptive control
- control method
- function approximation
- long run
- multi agent
- robot control
- active control
- structural information
- policy gradient
- control strategy
- stochastic control
- actor critic
- control system
- control strategies
- robotic control
- neural network
- partially observable environments
- multi agent systems
- markov decision processes
- reinforcement learning algorithms
- temporal difference