Safe and certified reinforcement learning with logical constraints

Thesis

Reinforcement Learning (RL) is a widely employed machine learning architecture that has been applied to a variety of decision-making problems, from resource management to robot locomotion, from recommendation systems to systems biology, and from traffic control to superhuman performance in video games. However, RL has experienced limited success beyond rigidly controlled or constrained applications, and successful employment of RL in safety-critical scenarios is yet to be achieved. A principa...

Expand abstract

Authors: Hasanbeig, MH

• Type of award: DPhil
• Level of award: Doctoral
• Awarding institution: University of Oxford
• Language: English
• Keywords: formal methods; Markov decision processes; reinforcement learning; policy synthesis; temporal logics
• Subjects: Machine learning; Verification (Logic); Reinforcement learning; Formal methods (Computer science)