Model Predictive Control-Based Reinforcement Learning Using Expected Sarsa.
Hoomaan MoradimaryamnegariMarco FregoAngelika PeerPublished in: IEEE Access (2022)
Keyphrases
- reinforcement learning
- model predictive control
- reinforcement learning algorithms
- function approximation
- predictive control
- control system
- temporal difference learning
- temporal difference
- state space
- learning algorithm
- action selection
- model free
- function approximators
- rl algorithms
- markov decision processes
- eligibility traces
- machine learning
- supervised learning
- reinforcement learning methods
- learning problems
- optimal policy
- fuzzy logic
- dynamic programming
- multi agent
- experimental data
- neural network