Lipschitz Lifelong Reinforcement Learning.
Erwan LecarpentierDavid AbelKavosh AsadiYuu JinnaiEmmanuel RachelsonMichael L. LittmanPublished in: AAAI (2021)
Keyphrases
- reinforcement learning
- function approximation
- state space
- model free
- robotic control
- learning algorithm
- multi agent
- learning process
- learning activities
- reinforcement learning algorithms
- pointwise
- st century
- learning scenarios
- policy search
- neural network
- markov decision process
- competence development
- transfer learning
- genetic algorithm
- machine learning
- learning classifier systems
- optimal control
- action selection
- temporal difference
- lifelong learning
- support vector
- action space
- temporal difference learning
- stochastic approximation
- information systems