Scaling up budgeted reinforcement learning.
Nicolas CarraraEdouard LeurentRomain LarocheTanguy UrvoyOdalric-Ambrym MaillardOlivier PietquinPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- state space
- model free
- reinforcement learning algorithms
- multi class
- machine learning
- temporal difference
- supervised learning
- robotic control
- multi agent
- database
- markov decision processes
- kernel classifiers
- learning algorithm
- learning problems
- monte carlo
- optimal control
- dynamic programming
- learning process
- action space
- learning agents
- autonomous learning
- relational reinforcement learning
- information retrieval
- data sets