Dual Policy-Based TD-Learning for Model Predictive Control.
Chang-Hun JiHo-Bin ChoiJoo-Seong HeoJu-Bong KimHyun-Kyo LimYoun-Hee HanPublished in: ICAIIC (2023)
Keyphrases
- model predictive control
- td learning
- temporal difference
- policy evaluation
- evaluation function
- predictive control
- control system
- function approximation
- action selection
- reinforcement learning
- average reward
- policy iteration
- function approximators
- least squares
- reinforcement learning problems
- reinforcement learning algorithms
- markov decision processes
- model free
- monte carlo
- optimal policy
- step size
- long run
- real time
- decision making
- variance reduction
- infinite horizon
- control policy
- multi step
- control scheme
- dynamic programming
- decision trees
- data mining