Function Approximation for Reinforcement Learning Controller for Energy from Spread Waves.
Soumyendu SarkarVineet GundechaSahand GhorbanpourAlexander ShmakovAshwin Ramesh BabuAvisek NaugAlexandre PichardMathieu CochoPublished in: IJCAI (2023)
Keyphrases
- function approximation
- reinforcement learning
- mountain car
- temporal difference
- actor critic
- model free
- adaptive control
- optimal control
- radial basis function
- temporal difference learning algorithms
- temporal difference learning
- function approximators
- learning tasks
- reinforcement learning algorithms
- control policy
- state space
- control system
- closed loop
- supervised learning
- control strategies
- control method
- control law
- markov decision processes
- decision trees
- learning algorithm
- control algorithm
- feedback control
- multi agent
- reinforcement learning problems
- reward function
- control strategy
- support vector
- policy gradient
- td learning
- training data