Lipschitz Lifelong Reinforcement Learning.
Erwan LecarpentierDavid AbelKavosh AsadiYuu JinnaiEmmanuel RachelsonMichael L. LittmanPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- function approximation
- state space
- pointwise
- model free
- machine learning
- multi agent
- optimal policy
- learning scenarios
- st century
- markov decision processes
- temporal difference learning
- action space
- optimal control
- lifelong learning
- data sets
- competence development
- learning classifier systems
- learning problems
- dynamical systems
- learning activities
- knowledge base
- learning algorithm