A Definition of Continual Reinforcement Learning.
David AbelAndré BarretoBenjamin Van RoyDoina PrecupHado Philip van HasseltSatinder SinghPublished in: NeurIPS (2023)
Keyphrases
- reinforcement learning
- learning algorithm
- function approximation
- machine learning
- model free
- state space
- databases
- relational reinforcement learning
- reinforcement learning methods
- learning agents
- reinforcement learning algorithms
- markov decision processes
- dynamic programming
- learning process
- artificial neural networks
- decision making
- information systems
- evolutionary algorithm
- optimal policy
- case study
- knowledge base
- temporal difference
- e learning
- transition model
- real time