Wield: Systematic Reinforcement Learning With Progressive Randomization.
Michael SchaarschmidtKai FrickeEiko YonekiPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- privacy preserving
- model free
- state space
- reinforcement learning algorithms
- markov decision processes
- learning algorithm
- privacy preserving association rule mining
- databases
- optimal policy
- supervised learning
- database
- learning capabilities
- robotic control
- real time
- dynamic programming
- bayesian networks
- knowledge base
- decision making
- artificial intelligence
- data mining
- continuous state
- multi agent reinforcement learning
- relational reinforcement learning
- perceptual aliasing