DSMC evaluation stages: fostering robust and safe behavior in deep reinforcement learning -- extended version

DOI10.1145/3607198MaRDI QIDQ6599368zbMATH OpenFDO

Authors Timo P. Gros, Joschka Groß, Daniel Höller, J. Hoffmann, Michaela Klauck, Hendrik Meerkamp, Nicola J. Müller, Lukas Schaller, Verena Wolf

Publication date 6 September 2024

Published in ACM Transactions on Modeling and Computer Simulation (Search for Journal in Brave)

zbMATH Keywords

deep reinforcement learningdeep statistical model checkingevaluation stages

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Specification and verification (program logics, model checking, etc.) (68Q60)

Recommendations

• Deep statistical model checking
• Planning for potential: efficient safe reinforcement learning
• Probabilistic counterexample guidance for safer reinforcement learning
• Tracking the race between deep reinforcement learning and imitation learning
• Deep ensemble reinforcement learning with multiple deep deterministic policy gradient algorithm

Cites work

• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• scientific article; zbMATH DE number 7559459 (Why is no real title available?)
• A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
• Computer Aided Verification
• Deep reinforcement learning with temporal logics
• Deep statistical model checking
• Expected policy gradients for reinforcement learning
• Planning and control in artificial intelligence: A unifying perspective
• Reinforcement learning. An introduction
• Run-time optimization for learned controllers through quantitative games
• Tools and Algorithms for the Construction and Analysis of Systems
• Tracking the race between deep reinforcement learning and imitation learning

This page was built for publication: DSMC evaluation stages: fostering robust and safe behavior in deep reinforcement learning -- extended version

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6599368)