Training Agents to Satisfy Timed and Untimed Signal Temporal Logic Specifications with Reinforcement Learning
- 1 October 2022
- book chapter
- Published by Springer Nature
- p. 190-206
Abstract
No abstract availableKeywords
This publication has 17 references indexed in Scilit:
- Grandmaster level in StarCraft II using multi-agent reinforcement learningNature, 2019
- LTL and Beyond: Formal Languages for Reward Function Specification in Reinforcement Learning2019
- Reinforcement learning with temporal logic rewards2017
- Q-Learning for robust satisfaction of signal temporal logic specifications2016
- Mastering the game of Go with deep neural networks and tree searchNature, 2016
- Human-level control through deep reinforcement learningNature, 2015
- Neural Fitted Q Iteration – First Experiences with a Data Efficient Neural Reinforcement Learning Method2005
- Monitoring Temporal Properties of Continuous Signals2004
- Q-learningMachine Learning, 1992
- Neuronlike adaptive elements that can solve difficult learning control problemsIEEE Transactions on Systems, Man, and Cybernetics, 1983