Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learning.
Kai-Chieh HsuVicenç Rúbies RoyoClaire J. TomlinJaime F. FisacPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- temporal difference
- learning algorithm
- function approximation
- state space
- markov decision processes
- learning process
- reinforcement learning algorithms
- optimal policy
- model free
- case study
- partially observable
- function approximators
- database
- road safety
- coal mining
- policy gradient
- partial observability
- optimal control
- hidden markov models