Shield Synthesis for Reinforcement Learning.
Bettina KönighoferFlorian LorberNils JansenRoderick BloemPublished in: ISoLA (1) (2020)
Keyphrases
- reinforcement learning
- model free
- program synthesis
- function approximation
- reinforcement learning algorithms
- neural network
- control problems
- learning algorithm
- multi agent
- dynamic programming
- robotic control
- temporal difference learning
- reinforcement learning methods
- optimal policy
- state space
- machine learning
- optimal control
- partially observable
- learning capabilities
- action selection
- texture synthesis
- database
- learning process
- real time