Options Discovery with Budgeted Reinforcement Learning.
Aurélia LéonLudovic DenoyerPublished in: CoRR (2016)
Keyphrases
- reinforcement learning
- multi class
- function approximation
- multi agent
- learning algorithm
- scientific discovery
- state space
- data mining
- learning process
- machine learning
- reinforcement learning algorithms
- markov decision processes
- model free
- robotic control
- online algorithms
- temporal difference
- action selection
- optimal policy
- dynamic programming
- discovery process
- robot control
- web services
- e learning
- feature selection