Virtuously Safe Reinforcement Learning.
Henrik AslundEl Mahdi El MhamdiRachid GuerraouiAlexandre MaurerPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- function approximation
- machine learning
- learning algorithm
- reinforcement learning algorithms
- state space
- multi agent
- optimal policy
- markov decision processes
- temporal difference
- model free
- robot control
- optimal control
- learning agents
- reinforcement learning methods
- expert systems
- artificial neural networks
- case study
- action selection
- knowledge base
- control problems
- direct policy search