Deep reinforcement learning with temporal logics

DOI10.1007/978-3-030-57628-8_1MaRDI QIDQ1996007zbMATH OpenOpenAlexFDO

Authors Mohammadhosein Hasanbeig, Daniel Kroening, Alessandro Abate

Publication date 2 March 2021

Full work available at URL https://doi.org/10.1007/978-3-030-57628-8_1

zbMATH Keywords

deep learninglinear temporal logiccontinuous-action Markov decision processescontinuous-state Markov decision processesmodel-free reinforcement learning

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Automata and formal grammars in connection with logical questions (03D05) Logic in artificial intelligence (68T27) Temporal logic (03B44)

Recommendations

• Deep Reinforcement Learning
• Deep reinforcement learning. Frontiers of artificial intelligence
• Deep reinforcement learning. Fundamentals, research and applications
• Certified reinforcement learning with logic guidance
• Temporal logic guided safe model-based reinforcement learning: a hybrid systems approach

Cites work

• scientific article; zbMATH DE number 1321699 (Why is no real title available?)
• scientific article; zbMATH DE number 5585443 (Why is no real title available?)
• Approximate model checking of stochastic hybrid systems
• Deep reinforcement learning with temporal logics
• Discounting the distant future: How much do uncertain rates increase valuations?
• Limit-deterministic Büchi automata for linear temporal logic
• Markov decision processes with state-dependent discount factors and unbounded rewards/costs
• Near-optimal reinforcement learning in polynomial time
• Omega-Regular Objectives in Model-Free Reinforcement Learning
• Reinforcement learning. An introduction
• Stochastic optimal control. The discrete time case
• Verifiably Safe Off-Model Reinforcement Learning
• Verification of Markov decision processes using learning algorithms
• \({\mathcal Q}\)-learning

Cited in

(22)

• Enforcing almost-sure reachability in POMDPs
• Learning that grid-convenience does not hurt resilience in the presence of uncertainty
• Regular decision processes
• Probabilistic reach-avoid for Bayesian neural networks
• Temporal logic guided safe model-based reinforcement learning: a hybrid systems approach
• Specification-guided reinforcement learning
• Deep reinforcement learning with temporal logics
• DSMC evaluation stages: fostering robust and safe behavior in deep reinforcement learning -- extended version
• Maximum causal entropy specification inference from demonstrations
• Automated verification and synthesis of stochastic hybrid systems: a survey
• Reward machines: exploiting reward function structure in reinforcement learning
• Planning for potential: efficient safe reinforcement learning
• Formal Policy Synthesis for Continuous-State Systems via Reinforcement Learning
• Verifiably safe exploration for end-to-end reinforcement learning
• Dynamic shielding for reinforcement learning in black-box environments
• Reusable contracts for safe integration of reinforcement learning in hybrid systems
• A framework for transforming specifications in reinforcement learning
• Policy synthesis and reinforcement learning for discounted LTL
• Certified reinforcement learning with logic guidance
• scientific article; zbMATH DE number 7559459 (Why is no real title available?)
• Inhomogeneous deep Q-network for time sensitive applications
• Probabilistic counterexample guidance for safer reinforcement learning

This page was built for publication: Deep reinforcement learning with temporal logics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1996007)