Choquet Regularization for Continuous-Time Reinforcement Learning.
Xia HanRuodu WangXun Yu ZhouPublished in: SIAM J. Control. Optim. (2023)
Keyphrases
- reinforcement learning
- optimal control
- state space
- function approximation
- markov processes
- reinforcement learning algorithms
- optimal policy
- markov chain
- dynamical systems
- learning algorithm
- iterative learning control
- model free
- multi agent
- markov decision processes
- learning process
- action selection
- regularization method
- regularization methods
- machine learning
- denoising
- supervised learning
- data dependent
- search space
- action space
- function approximators