Combining Q-learning and Deterministic Policy Gradient for Learning-Based MPC.
Katrine SeelSébastien GrosJan Tommy GravdahlPublished in: CDC (2023)
Keyphrases
- reinforcement learning
- learning algorithm
- policy gradient
- learning process
- cooperative
- actor critic
- reinforcement learning algorithms
- function approximation
- policy search
- learning tasks
- action selection
- state action
- neural network
- solving problems
- reinforcement learning methods
- domain independent
- state space
- computational complexity
- model free reinforcement learning