On reward distribution in reinforcement learning of multi-agent surveillance systems with temporal logic specifications.
Keita TerashimaKoichi KobayashiYuh YamashitaPublished in: Adv. Robotics (2024)
Keyphrases
- temporal logic
- reinforcement learning
- surveillance system
- multi agent
- concurrent systems
- transition systems
- model checking
- bounded model checking
- reactive systems
- model checker
- video surveillance
- formal specification language
- modal logic
- background subtraction
- formal specification
- reinforcement learning algorithms
- state space
- belief revision
- formal verification
- linear temporal logic
- markov decision processes
- optimal policy
- verification method
- ptz camera
- learning algorithm
- ptz cameras
- traffic surveillance
- mazurkiewicz traces
- reward function
- dynamic programming
- multi agent systems
- computer vision
- dynamic constraints
- smart camera
- single agent
- machine learning