Fill-and-Spill: Deep Reinforcement Learning Policy Gradient Methods for Reservoir Operation Decision and Control.
Sadegh Sadeghi TabasVidya SamadiPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- policy gradient methods
- control problems
- natural actor critic
- decision making
- policy gradient
- control system
- optimal control
- function approximation
- action selection
- control policy
- model free
- robot arm
- reinforcement learning algorithms
- function approximators
- multi agent
- optimal policy
- robotic systems
- adaptive control
- control method
- temporal difference
- decision processes
- reinforcement learning methods
- control strategies